vision-yolo-transfer
Query: YOLO object detection transfer learning
Results: 50
Date: 2026-07-07T18:53:16.525Z
1. MS-YOLO: Infrared Object Detection for Edge Deployment via MobileNetV4 and SlideLoss
Authors: Jiali Zhang, Thomas S. White, Haoliang Zhang, Wenqing Hu, Donald C. Wunsch, Jian Liu
Categories: cs.CV
Published: 2025-09-25
arXiv: 2509.21696v1
Abstract:
Infrared imaging has emerged as a robust solution for urban object detection under low-light and adverse weather conditions, offering significant advantages over traditional visible-light cameras. However, challenges such as class imbalance, thermal noise, and computational constraints can significantly hinder model performance in practical settings. To address these issues, we evaluate multiple YOLO variants on the FLIR ADAS V2 dataset, ultimately selecting YOLOv8 as our baseline due to its balanced accuracy and efficiency. Building on this foundation, we present \texttt{MS-YOLO} (\textbf{M}obileNetv4 and \textbf{S}lideLoss based on YOLO), which replaces YOLOv8’s CSPDarknet backbone with the more efficient MobileNetV4, reducing computational overhead by \textbf{1.5%} while sustaining high accuracy. In addition, we introduce \emph{SlideLoss}, a novel loss function that dynamically emphasizes under-represented and occluded samples, boosting precision without sacrificing recall. Experiments on the FLIR ADAS V2 benchmark show that \texttt{MS-YOLO} attains competitive mAP and superior precision while operating at only \textbf{6.7 GFLOPs}. These results demonstrate that \texttt{MS-YOLO} effectively addresses the dual challenge of maintaining high detection quality while minimizing computational costs, making it well-suited for real-time edge deployment in urban environments.
2. Oriented object detection in optical remote sensing images using deep learning: a survey
Authors: Kun Wang, Zi Wang, Zhang Li, Ang Su, Xichao Teng, Erting Pan, Minhao Liu, Qifeng Yu
Categories: cs.CV
Published: 2023-02-21
arXiv: 2302.10473v6
Abstract:
Oriented object detection is a fundamental yet challenging task in remote sensing (RS), aiming to locate and classify objects with arbitrary orientations. Recent advancements in deep learning have significantly enhanced the capabilities of oriented object detection methods. Given the rapid development of this field, a comprehensive survey of the recent advances in oriented object detection is presented in this paper. Specifically, we begin by tracing the technical evolution from horizontal object detection to oriented object detection and highlighting the specific related challenges, including feature misalignment, spatial misalignment, oriented bounding box (OBB) regression problems, and common issues encountered in RS. Subsequently, we further categorize the existing methods into detection frameworks, OBB regression techniques, feature representation approaches, and solutions to common issues and provide an in-depth discussion of how these methods address the above challenges. In addition, we cover several publicly available datasets and evaluation protocols. Furthermore, we provide a comprehensive comparison and analysis involving the state-of-the-art methods. Toward the end of this paper, we identify several future directions for oriented object detection research.
3. Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms
Authors: Ehsan Hallaji, Roozbeh Razavi-Far, Mehrdad Saif
Categories: cs.LG, cs.AI, cs.CR, cs.CV, cs.DC
Published: 2022-07-05
arXiv: 2207.02337v1
Abstract:
The advent of federated learning has facilitated large-scale data exchange amongst machine learning models while maintaining privacy. Despite its brief history, federated learning is rapidly evolving to make wider use more practical. One of the most significant advancements in this domain is the incorporation of transfer learning into federated learning, which overcomes fundamental constraints of primary federated learning, particularly in terms of security. This chapter performs a comprehensive survey on the intersection of federated and transfer learning from a security point of view. The main goal of this study is to uncover potential vulnerabilities and defense mechanisms that might compromise the privacy and performance of systems that use federated and transfer learning.
4. DAMO-YOLO : A Report on Real-Time Object Detection Design
Authors: Xianzhe Xu, Yiqi Jiang, Weihua Chen, Yilun Huang, Yuan Zhang, Xiuyu Sun
Categories: cs.CV
Published: 2022-11-23
arXiv: 2211.15444v4
Abstract:
In this report, we present a fast and accurate object detection method dubbed DAMO-YOLO, which achieves higher performance than the state-of-the-art YOLO series. DAMO-YOLO is extended from YOLO with some new technologies, including Neural Architecture Search (NAS), efficient Reparameterized Generalized-FPN (RepGFPN), a lightweight head with AlignedOTA label assignment, and distillation enhancement. In particular, we use MAE-NAS, a method guided by the principle of maximum entropy, to search our detection backbone under the constraints of low latency and high performance, producing ResNet/CSP-like structures with spatial pyramid pooling and focus modules. In the design of necks and heads, we follow the rule of ``large neck, small head’’.We import Generalized-FPN with accelerated queen-fusion to build the detector neck and upgrade its CSPNet with efficient layer aggregation networks (ELAN) and reparameterization. Then we investigate how detector head size affects detection performance and find that a heavy neck with only one task projection layer would yield better results.In addition, AlignedOTA is proposed to solve the misalignment problem in label assignment. And a distillation schema is introduced to improve performance to a higher level. Based on these new techs, we build a suite of models at various scales to meet the needs of different scenarios. For general industry requirements, we propose DAMO-YOLO-T/S/M/L. They can achieve 43.6/47.7/50.2/51.9 mAPs on COCO with the latency of 2.78/3.83/5.62/7.95 ms on T4 GPUs respectively. Additionally, for edge devices with limited computing power, we have also proposed DAMO-YOLO-Ns/Nm/Nl lightweight models. They can achieve 32.3/38.2/40.5 mAPs on COCO with the latency of 4.08/5.05/6.69 ms on X86-CPU. Our proposed general and lightweight models have outperformed other YOLO series models in their respective application scenarios.
5. SPMamba-YOLO: An Underwater Object Detection Network Based on Multi-Scale Feature Enhancement and Global Context Modeling
Authors: Guanghao Liao, Zhen Liu, Liyuan Cao, Yonghui Yang, Qi Li
Categories: cs.CV
Published: 2026-02-26
arXiv: 2602.22674v1
Abstract:
Underwater object detection is a critical yet challenging research problem owing to severe light attenuation, color distortion, background clutter, and the small scale of underwater targets. To address these challenges, we propose SPMamba-YOLO, a novel underwater object detection network that integrates multi-scale feature enhancement with global context modeling. Specifically, a Spatial Pyramid Pooling Enhanced Layer Aggregation Network (SPPELAN) module is introduced to strengthen multi-scale feature aggregation and expand the receptive field, while a Pyramid Split Attention (PSA) mechanism enhances feature discrimination by emphasizing informative regions and suppressing background interference. In addition, a Mamba-based state space modeling module is incorporated to efficiently capture long-range dependencies and global contextual information, thereby improving detection robustness in complex underwater environments. Extensive experiments on the URPC2022 dataset demonstrate that SPMamba-YOLO outperforms the YOLOv8n baseline by more than 4.9% in mAP@0.5, particularly for small and densely distributed underwater objects, while maintaining a favorable balance between detection accuracy and computational cost.
6. YOLO-IOD: Towards Real Time Incremental Object Detection
Authors: Shizhou Zhang, Xueqiang Lv, Yinghui Xing, Qirui Wu, Di Xu, Chen Zhao, Yanning Zhang
Categories: cs.CV
Published: 2025-12-28
arXiv: 2512.22973v2
Abstract:
Current methods for incremental object detection (IOD) primarily rely on Faster R-CNN or DETR series detectors; however, these approaches do not accommodate the real-time YOLO detection frameworks. In this paper, we first identify three primary types of knowledge conflicts that contribute to catastrophic forgetting in YOLO-based incremental detectors: foreground-background confusion, parameter interference, and misaligned knowledge distillation. Subsequently, we introduce YOLO-IOD, a real-time Incremental Object Detection (IOD) framework that is constructed upon the pretrained YOLO-World model, facilitating incremental learning via a stage-wise parameter-efficient fine-tuning process. Specifically, YOLO-IOD encompasses three principal components: 1) Conflict-Aware Pseudo-Label Refinement (CPR), which mitigates the foreground-background confusion by leveraging the confidence levels of pseudo labels and identifying potential objects relevant to future tasks. 2) Importancebased Kernel Selection (IKS), which identifies and updates the pivotal convolution kernels pertinent to the current task during the current learning stage. 3) Cross-Stage Asymmetric Knowledge Distillation (CAKD), which addresses the misaligned knowledge distillation conflict by transmitting the features of the student target detector through the detection heads of both the previous and current teacher detectors, thereby facilitating asymmetric distillation between existing and newly introduced categories. We further introduce LoCo COCO, a more realistic benchmark that eliminates data leakage across stages. Experiments on both conventional and LoCo COCO benchmarks show that YOLO-IOD achieves superior performance with minimal forgetting.
7. YOLO-World: Real-Time Open-Vocabulary Object Detection
Authors: Tianheng Cheng, Lin Song, Yixiao Ge, Wenyu Liu, Xinggang Wang, Ying Shan
Categories: cs.CV
Published: 2024-01-30
arXiv: 2401.17270v3
Abstract:
The You Only Look Once (YOLO) series of detectors have established themselves as efficient and practical tools. However, their reliance on predefined and trained object categories limits their applicability in open scenarios. Addressing this limitation, we introduce YOLO-World, an innovative approach that enhances YOLO with open-vocabulary detection capabilities through vision-language modeling and pre-training on large-scale datasets. Specifically, we propose a new Re-parameterizable Vision-Language Path Aggregation Network (RepVL-PAN) and region-text contrastive loss to facilitate the interaction between visual and linguistic information. Our method excels in detecting a wide range of objects in a zero-shot manner with high efficiency. On the challenging LVIS dataset, YOLO-World achieves 35.4 AP with 52.0 FPS on V100, which outperforms many state-of-the-art methods in terms of both accuracy and speed. Furthermore, the fine-tuned YOLO-World achieves remarkable performance on several downstream tasks, including object detection and open-vocabulary instance segmentation.
8. Transfer Learning Toolkit: Primers and Benchmarks
Authors: Fuzhen Zhuang, Keyu Duan, Tongjia Guo, Yongchun Zhu, Dongbo Xi, Zhiyuan Qi, Qing He
Categories: cs.LG, stat.ML
Published: 2019-11-20
arXiv: 1911.08967v1
Abstract:
The transfer learning toolkit wraps the codes of 17 transfer learning models and provides integrated interfaces, allowing users to use those models by calling a simple function. It is easy for primary researchers to use this toolkit and to choose proper models for real-world applications. The toolkit is written in Python and distributed under MIT open source license. In this paper, the current state of this toolkit is described and the necessary environment setting and usage are introduced.
9. D-YOLO a robust framework for object detection in adverse weather conditions
Authors: Zihan Chu
Categories: cs.CV, eess.IV
Published: 2024-03-14
arXiv: 2403.09233v2
Abstract:
Adverse weather conditions including haze, snow and rain lead to decline in image qualities, which often causes a decline in performance for deep-learning based detection networks. Most existing approaches attempts to rectify hazy images before performing object detection, which increases the complexity of the network and may result in the loss in latent information. To better integrate image restoration and object detection tasks, we designed a double-route network with an attention feature fusion module, taking both hazy and dehazed features into consideration. We also proposed a subnetwork to provide haze-free features to the detection network. Specifically, our D-YOLO improves the performance of the detection network by minimizing the distance between the clear feature extraction subnetwork and detection network. Experiments on RTTS and FoggyCityscapes datasets show that D-YOLO demonstrates better performance compared to the state-of-the-art methods. It is a robust detection framework for bridging the gap between low-level dehazing and high-level detection.
10. YOLO-CL: Galaxy cluster detection in the SDSS with deep machine learning
Authors: Kirill Grishin, Simona Mei, Stéphane Ilic
Categories: astro-ph.CO, astro-ph.GA
Published: 2023-01-23
arXiv: 2301.09657v2
Abstract:
(Abridged) Galaxy clusters are a powerful probe of cosmological models. Next generation large-scale optical and infrared surveys will reach unprecedented depths over large areas and require highly complete and pure cluster catalogs, with a well defined selection function. We have developed a new cluster detection algorithm YOLO-CL, which is a modified version of the state-of-the-art object detection deep convolutional network YOLO, optimized for the detection of galaxy clusters. We trained YOLO-CL on color images of the redMaPPer cluster detections in the SDSS. We find that YOLO-CL detects $95-98%$ of the redMaPPer clusters, with a purity of $95-98%$ calculated by applying the network to SDSS blank fields. When compared to the MCXC2021 X-ray catalog in the SDSS footprint,YOLO-CL is more complete then redMaPPer, which means that the neural network improved the cluster detection efficiency of its training sample. The YOLO-CL selection function is approximately constant with redshift, with respect to the MCXC2021 cluster mean X-ray surface brightness. YOLO-CL shows high performance when compared to traditional detection algorithms applied to SDSS. Deep learning networks benefit from a strong advantage over traditional galaxy cluster detection techniques because they do not need galaxy photometric and photometric redshift catalogs. This eliminates systematic uncertainties that can be introduced during source detection, and photometry and photometric redshift measurements. Our results show that YOLO-CL is an efficient alternative to traditional cluster detection methods. In general, this work shows that it is worth exploring the performance of deep convolution networks for future cosmological cluster surveys, such as the Rubin/LSST, Euclid or the Roman Space Telescope surveys.
11. Top-Related Meta-Learning Method for Few-Shot Object Detection
Authors: Qian Li, Nan Guo, Xiaochun Ye, Duo Wang, Dongrui Fan, Zhimin Tang
Categories: cs.CV, cs.LG
Published: 2020-07-14
arXiv: 2007.06837v6
Abstract:
Many meta-learning methods are proposed for few-shot detection. However, previous most methods have two main problems, poor detection APs, and strong bias because of imbalance and insufficient datasets. Previous works mainly alleviate these issues by additional datasets, multi-relation attention mechanisms and sub-modules. However, they require more cost. In this work, for meta-learning, we find that the main challenges focus on related or irrelevant semantic features between categories. Therefore, based on semantic features, we propose a Top-C classification loss (i.e., TCL-C) for classification task and a category-based grouping mechanism for category-based meta-features obtained by the meta-model. The TCL-C exploits the true-label prediction and the most likely C-1 false classification predictions to improve detection performance on few-shot classes. According to similar appearance (i.e., visual appearance, shape, and limbs etc.) and environment in which objects often appear, the category-based grouping mechanism splits categories into disjoint groups to make similar semantic features more compact between categories within a group and obtain more significant difference between groups, alleviating the strong bias problem and further improving detection APs. The whole training consists of the base model and the fine-tuning phases. According to grouping mechanism, we group the meta-features vectors obtained by meta-model, so that the distribution difference between groups is obvious, and the one within each group is less. Extensive experiments on Pascal VOC dataset demonstrate that ours which combines the TCL-C with category-based grouping significantly outperforms previous state-of-the-art methods for few-shot detection. Compared with previous competitive baseline, ours improves detection APs by almost 4% for few-shot detection.
12. Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection
Authors: Thang Doan, Xin Li, Sima Behpour, Wenbin He, Liang Gou, Liu Ren
Categories: cs.CV, cs.LG
Published: 2023-06-25
arXiv: 2306.14291v4
Abstract:
Open World Object Detection (OWOD) is a challenging and realistic task that extends beyond the scope of standard Object Detection task. It involves detecting both known and unknown objects while integrating learned knowledge for future tasks. However, the level of “unknownness” varies significantly depending on the context. For example, a tree is typically considered part of the background in a self-driving scene, but it may be significant in a household context. We argue that this contextual information should already be embedded within the known classes. In other words, there should be a semantic or latent structure relationship between the known and unknown items to be discovered. Motivated by this observation, we propose Hyp-OW, a method that learns and models hierarchical representation of known items through a SuperClass Regularizer. Leveraging this representation allows us to effectively detect unknown objects using a similarity distance-based relabeling module. Extensive experiments on benchmark datasets demonstrate the effectiveness of Hyp-OW, achieving improvement in both known and unknown detection (up to 6 percent). These findings are particularly pronounced in our newly designed benchmark, where a strong hierarchical structure exists between known and unknown objects. Our code can be found at https://github.com/boschresearch/Hyp-OW
13. Predicting concentration levels of air pollutants by transfer learning and recurrent neural network
Authors: Iat Hang Fong, Tengyue Li, Simon Fong, Raymond K. Wong, Antonio J. Tallón-Ballesteros
Categories: cs.LG, cs.NE, physics.ao-ph
Published: 2025-01-30
arXiv: 2502.01654v1
Abstract:
Air pollution (AP) poses a great threat to human health, and people are paying more attention than ever to its prediction. Accurate prediction of AP helps people to plan for their outdoor activities and aids protecting human health. In this paper, long-short term memory (LSTM) recurrent neural networks (RNNs) have been used to predict the future concentration of air pollutants (APS) in Macau. Additionally, meteorological data and data on the concentration of APS have been utilized. Moreover, in Macau, some air quality monitoring stations (AQMSs) have less observed data in quantity, and, at the same time, some AQMSs recorded less observed data of certain types of APS. Therefore, the transfer learning and pre-trained neural networks have been employed to assist AQMSs with less observed data to build a neural network with high prediction accuracy. The experimental sample covers a period longer than 12-year and includes daily measurements from several APS as well as other more classical meteorological values. Records from five stations, four out of them are AQMSs and the remaining one is an automatic weather station, have been prepared from the aforesaid period and eventually underwent to computational intelligence techniques to build and extract a prediction knowledge-based system. As shown by experimentation, LSTM RNNs initialized with transfer learning methods have higher prediction accuracy; it incurred shorter training time than randomly initialized recurrent neural networks.
14. Transfer Learning and Organic Computing for Autonomous Vehicles
Authors: Christofer Fellicious
Categories: cs.LG, cs.RO, stat.ML
Published: 2018-08-16
arXiv: 1808.05443v1
Abstract:
Autonomous Vehicles(AV) are one of the brightest promises of the future which would help cut down fatalities and improve travel time while working in harmony. Autonomous vehicles will face with challenging situations and experiences not seen before. These experiences should be converted to knowledge and help the vehicle prepare better in the future. Online Transfer Learning will help transferring prior knowledge to a new task and also keep the knowledge updated as the task evolves. This paper presents the different methods of transfer learning, online transfer learning and organic computing that could be adapted to the domain of autonomous vehicles.
15. TransferD2: Automated Defect Detection Approach in Smart Manufacturing using Transfer Learning Techniques
Authors: Atah Nuh Mih, Hung Cao, Joshua Pickard, Monica Wachowicz, Rickey Dubay
Categories: cs.CV, cs.AI, cs.LG
Published: 2023-02-26
arXiv: 2302.13317v1
Abstract:
Quality assurance is crucial in the smart manufacturing industry as it identifies the presence of defects in finished products before they are shipped out. Modern machine learning techniques can be leveraged to provide rapid and accurate detection of these imperfections. We, therefore, propose a transfer learning approach, namely TransferD2, to correctly identify defects on a dataset of source objects and extend its application to new unseen target objects. We present a data enhancement technique to generate a large dataset from the small source dataset for building a classifier. We then integrate three different pre-trained models (Xception, ResNet101V2, and InceptionResNetV2) into the classifier network and compare their performance on source and target data. We use the classifier to detect the presence of imperfections on the unseen target data using pseudo-bounding boxes. Our results show that ResNet101V2 performs best on the source data with an accuracy of 95.72%. Xception performs best on the target data with an accuracy of 91.00% and also provides a more accurate prediction of the defects on the target images. Throughout the experiment, the results also indicate that the choice of a pre-trained model is not dependent on the depth of the network. Our proposed approach can be applied in defect detection applications where insufficient data is available for training a model and can be extended to identify imperfections in new unseen data.
16. An Empirical Study Of Self-supervised Learning Approaches For Object Detection With Transformers
Authors: Gokul Karthik Kumar, Sahal Shaji Mullappilly, Abhishek Singh Gehlot
Categories: cs.CV, cs.AI, cs.LG
Published: 2022-05-11
arXiv: 2205.05543v1
Abstract:
Self-supervised learning (SSL) methods such as masked language modeling have shown massive performance gains by pretraining transformer models for a variety of natural language processing tasks. The follow-up research adapted similar methods like masked image modeling in vision transformer and demonstrated improvements in the image classification task. Such simple self-supervised methods are not exhaustively studied for object detection transformers (DETR, Deformable DETR) as their transformer encoder modules take input in the convolutional neural network (CNN) extracted feature space rather than the image space as in general vision transformers. However, the CNN feature maps still maintain the spatial relationship and we utilize this property to design self-supervised learning approaches to train the encoder of object detection transformers in pretraining and multi-task learning settings. We explore common self-supervised methods based on image reconstruction, masked image modeling and jigsaw. Preliminary experiments in the iSAID dataset demonstrate faster convergence of DETR in the initial epochs in both pretraining and multi-task learning settings; nonetheless, similar improvement is not observed in the case of multi-task learning with Deformable DETR. The code for our experiments with DETR and Deformable DETR are available at https://github.com/gokulkarthik/detr and https://github.com/gokulkarthik/Deformable-DETR respectively.
17. A Survey of Self-Supervised and Few-Shot Object Detection
Authors: Gabriel Huang, Issam Laradji, David Vazquez, Simon Lacoste-Julien, Pau Rodriguez
Categories: cs.CV, cs.AI, cs.LG
Published: 2021-10-27
arXiv: 2110.14711v3
Abstract:
Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a model on novel (unseen) object classes with little data, it still requires prior training on many labeled examples of base (seen) classes. On the other hand, self-supervised methods aim at learning representations from unlabeled data which transfer well to downstream tasks such as object detection. Combining few-shot and self-supervised object detection is a promising research direction. In this survey, we review and characterize the most recent approaches on few-shot and self-supervised object detection. Then, we give our main takeaways and discuss future research directions. Project page at https://gabrielhuang.github.io/fsod-survey/
18. Transferability in Deep Learning: A Survey
Authors: Junguang Jiang, Yang Shu, Jianmin Wang, Mingsheng Long
Categories: cs.LG
Published: 2022-01-15
arXiv: 2201.05867v1
Abstract:
The success of deep learning algorithms generally depends on large-scale data, while humans appear to have inherent ability of knowledge transfer, by recognizing and applying relevant knowledge from previous learning experiences when encountering and solving unseen tasks. Such an ability to acquire and reuse knowledge is known as transferability in deep learning. It has formed the long-term quest towards making deep learning as data-efficient as human learning, and has been motivating fruitful design of more powerful deep learning algorithms. We present this survey to connect different isolated areas in deep learning with their relation to transferability, and to provide a unified and complete view to investigating transferability through the whole lifecycle of deep learning. The survey elaborates the fundamental goals and challenges in parallel with the core principles and methods, covering recent cornerstones in deep architectures, pre-training, task adaptation and domain adaptation. This highlights unanswered questions on the appropriate objectives for learning transferable knowledge and for adapting the knowledge to new tasks and domains, avoiding catastrophic forgetting and negative transfer. Finally, we implement a benchmark and an open-source library, enabling a fair evaluation of deep learning methods in terms of transferability.
19. Transfer Learning with Pre-trained Conditional Generative Models
Authors: Shin’ya Yamaguchi, Sekitoshi Kanai, Atsutoshi Kumagai, Daiki Chijiwa, Hisashi Kashima
Categories: cs.LG, cs.AI, stat.ML
Published: 2022-04-27
arXiv: 2204.12833v3
Abstract:
Transfer learning is crucial in training deep neural networks on new target tasks. Current transfer learning methods always assume at least one of (i) source and target task label spaces overlap, (ii) source datasets are available, and (iii) target network architectures are consistent with source ones. However, holding these assumptions is difficult in practical settings because the target task rarely has the same labels as the source task, the source dataset access is restricted due to storage costs and privacy, and the target architecture is often specialized to each task. To transfer source knowledge without these assumptions, we propose a transfer learning method that uses deep generative models and is composed of the following two stages: pseudo pre-training (PP) and pseudo semi-supervised learning (P-SSL). PP trains a target architecture with an artificial dataset synthesized by using conditional source generative models. P-SSL applies SSL algorithms to labeled target data and unlabeled pseudo samples, which are generated by cascading the source classifier and generative models to condition them with target samples. Our experimental results indicate that our method can outperform the baselines of scratch training and knowledge distillation.
20. Transfer Learning for Kernel-based Regression
Authors: Chao Wang, Caixing Wang, Xin He, Xingdong Feng
Categories: stat.ML, cs.LG, stat.ME
Published: 2023-10-21
arXiv: 2310.13966v3
Abstract:
In recent years, transfer learning has garnered significant attention. Its ability to leverage knowledge from related studies to improve generalization performance in a target study has made it highly appealing. This paper focuses on investigating the transfer learning problem within the context of nonparametric regression over a reproducing kernel Hilbert space. The aim is to bridge the gap between practical effectiveness and theoretical guarantees. We specifically consider two scenarios: one where the transferable sources are known and another where they are unknown. For the known transferable source case, we propose a two-step kernel-based estimator by solely using kernel ridge regression. For the unknown case, we develop a novel method based on an efficient aggregation algorithm, which can automatically detect and alleviate the effects of negative sources. This paper provides the statistical properties of the desired estimators and establishes the minimax rate. Through extensive numerical experiments on synthetic data and real examples, we validate our theoretical findings and demonstrate the effectiveness of our proposed method.
21. How good are variational autoencoders at transfer learning?
Authors: Lisa Bonheme, Marek Grzes
Categories: cs.LG
Published: 2023-04-21
arXiv: 2304.10767v1
Abstract:
Variational autoencoders (VAEs) are used for transfer learning across various research domains such as music generation or medical image analysis. However, there is no principled way to assess before transfer which components to retrain or whether transfer learning is likely to help on a target task. We propose to explore this question through the lens of representational similarity. Specifically, using Centred Kernel Alignment (CKA) to evaluate the similarity of VAEs trained on different datasets, we show that encoders’ representations are generic but decoders’ specific. Based on these insights, we discuss the implications for selecting which components of a VAE to retrain and propose a method to visually assess whether transfer learning is likely to help on classification tasks.
22. Object Contour and Edge Detection with RefineContourNet
Authors: Andre Peter Kelm, Vijesh Soorya Rao, Udo Zoelzer
Categories: cs.CV, cs.LG
Published: 2019-04-30
arXiv: 1904.13353v2
Abstract:
A ResNet-based multi-path refinement CNN is used for object contour detection. For this task, we prioritise the effective utilization of the high-level abstraction capability of a ResNet, which leads to state-of-the-art results for edge detection. Keeping our focus in mind, we fuse the high, mid and low-level features in that specific order, which differs from many other approaches. It uses the tensor with the highest-levelled features as the starting point to combine it layer-by-layer with features of a lower abstraction level until it reaches the lowest level. We train this network on a modified PASCAL VOC 2012 dataset for object contour detection and evaluate on a refined PASCAL-val dataset reaching an excellent performance and an Optimal Dataset Scale (ODS) of 0.752. Furthermore, by fine-training on the BSDS500 dataset we reach state-of-the-art results for edge-detection with an ODS of 0.824.
23. A Transfer Learning and Optimized CNN Based Intrusion Detection System for Internet of Vehicles
Authors: Li Yang, Abdallah Shami
Categories: cs.CR, cs.AI, cs.CV, cs.LG, cs.NI
Published: 2022-01-27
arXiv: 2201.11812v1
Abstract:
Modern vehicles, including autonomous vehicles and connected vehicles, are increasingly connected to the external world, which enables various functionalities and services. However, the improving connectivity also increases the attack surfaces of the Internet of Vehicles (IoV), causing its vulnerabilities to cyber-threats. Due to the lack of authentication and encryption procedures in vehicular networks, Intrusion Detection Systems (IDSs) are essential approaches to protect modern vehicle systems from network attacks. In this paper, a transfer learning and ensemble learning-based IDS is proposed for IoV systems using convolutional neural networks (CNNs) and hyper-parameter optimization techniques. In the experiments, the proposed IDS has demonstrated over 99.25% detection rates and F1-scores on two well-known public benchmark IoV security datasets: the Car-Hacking dataset and the CICIDS2017 dataset. This shows the effectiveness of the proposed IDS for cyber-attack detection in both intra-vehicle and external vehicular networks.
24. Exploring Depth Contribution for Camouflaged Object Detection
Authors: Mochu Xiang, Jing Zhang, Yunqiu Lv, Aixuan Li, Yiran Zhong, Yuchao Dai
Categories: cs.CV
Published: 2021-06-24
arXiv: 2106.13217v3
Abstract:
Camouflaged object detection (COD) aims to segment camouflaged objects hiding in the environment, which is challenging due to the similar appearance of camouflaged objects and their surroundings. Research in biology suggests depth can provide useful object localization cues for camouflaged object discovery. In this paper, we study the depth contribution for camouflaged object detection, where the depth maps are generated with existing monocular depth estimation (MDE) methods. Due to the domain gap between the MDE dataset and our COD dataset, the generated depth maps are not accurate enough to be directly used. We then introduce two solutions to avoid the noisy depth maps from dominating the training process. Firstly, we present an auxiliary depth estimation branch (“ADE”), aiming to regress the depth maps. We find that “ADE” is especially necessary for our “generated depth” scenario. Secondly, we introduce a multi-modal confidence-aware loss function via a generative adversarial network to weigh the contribution of depth for camouflaged object detection. Our extensive experiments on various camouflaged object detection datasets explain that the existing “sensor depth” based RGB-D segmentation techniques work poorly with “generated depth”, and our proposed two solutions work cooperatively, achieving effective depth contribution exploration for camouflaged object detection.
25. PVAFN: Point-Voxel Attention Fusion Network with Multi-Pooling Enhancing for 3D Object Detection
Authors: Yidi Li, Jiahao Wen, Bin Ren, Wenhao Li, Zhenhuan Xu, Hao Guo, Hong Liu, Nicu Sebe
Categories: cs.CV
Published: 2024-08-26
arXiv: 2408.14600v1
Abstract:
The integration of point and voxel representations is becoming more common in LiDAR-based 3D object detection. However, this combination often struggles with capturing semantic information effectively. Moreover, relying solely on point features within regions of interest can lead to information loss and limitations in local feature representation. To tackle these challenges, we propose a novel two-stage 3D object detector, called Point-Voxel Attention Fusion Network (PVAFN). PVAFN leverages an attention mechanism to improve multi-modal feature fusion during the feature extraction phase. In the refinement stage, it utilizes a multi-pooling strategy to integrate both multi-scale and region-specific information effectively. The point-voxel attention mechanism adaptively combines point cloud and voxel-based Bird’s-Eye-View (BEV) features, resulting in richer object representations that help to reduce false detections. Additionally, a multi-pooling enhancement module is introduced to boost the model’s perception capabilities. This module employs cluster pooling and pyramid pooling techniques to efficiently capture key geometric details and fine-grained shape structures, thereby enhancing the integration of local and global features. Extensive experiments on the KITTI and Waymo datasets demonstrate that the proposed PVAFN achieves competitive performance. The code and models will be available.
26. G5: A Universal GRAPH-BERT for Graph-to-Graph Transfer and Apocalypse Learning
Authors: Jiawei Zhang
Categories: cs.LG, cs.NE, cs.SI, stat.ML
Published: 2020-06-11
arXiv: 2006.06183v1
Abstract:
The recent GRAPH-BERT model introduces a new approach to learning graph representations merely based on the attention mechanism. GRAPH-BERT provides an opportunity for transferring pre-trained models and learned graph representations across different tasks within the same graph dataset. In this paper, we will further investigate the graph-to-graph transfer of a universal GRAPH-BERT for graph representation learning across different graph datasets, and our proposed model is also referred to as the G5 for simplicity. Many challenges exist in learning G5 to adapt the distinct input and output configurations for each graph data source, as well as the information distributions differences. G5 introduces a pluggable model architecture: (a) each data source will be pre-processed with a unique input representation learning component; (b) each output application task will also have a specific functional component; and (c) all such diverse input and output components will all be conjuncted with a universal GRAPH-BERT core component via an input size unification layer and an output representation fusion layer, respectively. The G5 model removes the last obstacle for cross-graph representation learning and transfer. For the graph sources with very sparse training data, the G5 model pre-trained on other graphs can still be utilized for representation learning with necessary fine-tuning. What’s more, the architecture of G5 also allows us to learn a supervised functional classifier for data sources without any training data at all. Such a problem is also named as the Apocalypse Learning task in this paper. Two different label reasoning strategies, i.e., Cross-Source Classification Consistency Maximization (CCCM) and Cross-Source Dynamic Routing (CDR), are introduced in this paper to address the problem.
27. Data Quality Monitoring for the Hadron Calorimeters Using Transfer Learning for Anomaly Detection
Authors: Mulugeta Weldezgina Asres, Christian Walter Omlin, Long Wang, Pavel Parygin, David Yu, Jay Dittmann, The CMS-HCAL Collaboration
Categories: cs.LG
Published: 2024-08-29
arXiv: 2408.16612v3
Abstract:
The proliferation of sensors brings an immense volume of spatio-temporal (ST) data in many domains, including monitoring, diagnostics, and prognostics applications. Data curation is a time-consuming process for a large volume of data, making it challenging and expensive to deploy data analytics platforms in new environments. Transfer learning (TL) mechanisms promise to mitigate data sparsity and model complexity by utilizing pre-trained models for a new task. Despite the triumph of TL in fields like computer vision and natural language processing, efforts on complex ST models for anomaly detection (AD) applications are limited. In this study, we present the potential of TL within the context of high-dimensional ST AD with a hybrid autoencoder architecture, incorporating convolutional, graph, and recurrent neural networks. Motivated by the need for improved model accuracy and robustness, particularly in scenarios with limited training data on systems with thousands of sensors, this research investigates the transferability of models trained on different sections of the Hadron Calorimeter of the Compact Muon Solenoid experiment at CERN. The key contributions of the study include exploring TL’s potential and limitations within the context of encoder and decoder networks, revealing insights into model initialization and training configurations that enhance performance while substantially reducing trainable parameters and mitigating data contamination effects. Code: https://github.com/muleina/CMS_HCAL_ML_OnlineDQM .
28. Exploring Diversity-based Active Learning for 3D Object Detection in Autonomous Driving
Authors: Jinpeng Lin, Zhihao Liang, Shengheng Deng, Lile Cai, Tao Jiang, Tianrui Li, Kui Jia, Xun Xu
Categories: cs.CV
Published: 2022-05-16
arXiv: 2205.07708v3
Abstract:
3D object detection has recently received much attention due to its great potential in autonomous vehicle (AV). The success of deep learning based object detectors relies on the availability of large-scale annotated datasets, which is time-consuming and expensive to compile, especially for 3D bounding box annotation. In this work, we investigate diversity-based active learning (AL) as a potential solution to alleviate the annotation burden. Given limited annotation budget, only the most informative frames and objects are automatically selected for human to annotate. Technically, we take the advantage of the multimodal information provided in an AV dataset, and propose a novel acquisition function that enforces spatial and temporal diversity in the selected samples. We benchmark the proposed method against other AL strategies under realistic annotation cost measurement, where the realistic costs for annotating a frame and a 3D bounding box are both taken into consideration. We demonstrate the effectiveness of the proposed method on the nuScenes dataset and show that it outperforms existing AL strategies significantly. Code is available at https://github.com/Linkon87/Exploring-Diversity-based-Active-Learning-for-3D-Object-Detection-in-Autonomous-Driving
29. Deep Transfer Learning-Assisted Signal Detection for Ambient Backscatter Communications
Authors: Chang Liu, Xuemeng Liu, Zhiqiang Wei, Derrick Wing Kwan Ng, Jinhong Yuan, Ying-Chang Liang
Categories: eess.SP, cs.IT
Published: 2020-11-10
arXiv: 2011.05574v1
Abstract:
Existing tag signal detection algorithms inevitably suffer from a high bit error rate (BER) due to the difficulties in estimating the channel state information (CSI). To eliminate the requirement of channel estimation and to improve the system performance, in this paper, we adopt a deep transfer learning (DTL) approach to implicitly extract the features of communication channel and directly recover tag symbols. Inspired by the powerful capability of convolutional neural networks (CNN) in exploring the features of data in a matrix form, we design a novel covariance matrix aware neural network (CMNet)-based detection scheme to facilitate DTL for tag signal detection, which consists of offline learning, transfer learning, and online detection. Specifically, a CMNet-based likelihood ratio test (CMNet-LRT) is derived based on the minimum error probability (MEP) criterion. Taking advantage of the outstanding performance of DTL in transferring knowledge with only a few training data, the proposed scheme can adaptively fine-tune the detector for different channel environments to further improve the detection performance. Finally, extensive simulation results demonstrate that the BER performance of the proposed method is comparable to that of the optimal detection method with perfect CSI.
30. TJU-DHD: A Diverse High-Resolution Dataset for Object Detection
Authors: Yanwei Pang, Jiale Cao, Yazhao Li, Jin Xie, Hanqing Sun, Jinfeng Gong
Categories: cs.CV
Published: 2020-11-18
arXiv: 2011.09170v1
Abstract:
Vehicles, pedestrians, and riders are the most important and interesting objects for the perception modules of self-driving vehicles and video surveillance. However, the state-of-the-art performance of detecting such important objects (esp. small objects) is far from satisfying the demand of practical systems. Large-scale, rich-diversity, and high-resolution datasets play an important role in developing better object detection methods to satisfy the demand. Existing public large-scale datasets such as MS COCO collected from websites do not focus on the specific scenarios. Moreover, the popular datasets (e.g., KITTI and Citypersons) collected from the specific scenarios are limited in the number of images and instances, the resolution, and the diversity. To attempt to solve the problem, we build a diverse high-resolution dataset (called TJU-DHD). The dataset contains 115,354 high-resolution images (52% images have a resolution of 1624$\times$1200 pixels and 48% images have a resolution of at least 2,560$\times$1,440 pixels) and 709,330 labeled objects in total with a large variance in scale and appearance. Meanwhile, the dataset has a rich diversity in season variance, illumination variance, and weather variance. In addition, a new diverse pedestrian dataset is further built. With the four different detectors (i.e., the one-stage RetinaNet, anchor-free FCOS, two-stage FPN, and Cascade R-CNN), experiments about object detection and pedestrian detection are conducted. We hope that the newly built dataset can help promote the research on object detection and pedestrian detection in these two scenes. The dataset is available at https://github.com/tjubiit/TJU-DHD.
31. Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach
Authors: Matthias Bartolo, Dylan Seychell, Gabriel Hili, Matthew Montebello, Carl James Debono, Saviour Formosa, Konstantinos Makantasis
Categories: cs.CV, cs.AI, cs.ET, cs.LG
Published: 2026-01-05
arXiv: 2601.02016v1
Abstract:
This paper investigates the integration of the Learning Using Privileged Information (LUPI) paradigm in object detection to exploit fine-grained, descriptive information available during training but not at inference. We introduce a general, model-agnostic methodology for injecting privileged information-such as bounding box masks, saliency maps, and depth cues-into deep learning-based object detectors through a teacher-student architecture. Experiments are conducted across five state-of-the-art object detection models and multiple public benchmarks, including UAV-based litter detection datasets and Pascal VOC 2012, to assess the impact on accuracy, generalization, and computational efficiency. Our results demonstrate that LUPI-trained students consistently outperform their baseline counterparts, achieving significant boosts in detection accuracy with no increase in inference complexity or model size. Performance improvements are especially marked for medium and large objects, while ablation studies reveal that intermediate weighting of teacher guidance optimally balances learning from privileged and standard inputs. The findings affirm that the LUPI framework provides an effective and practical strategy for advancing object detection systems in both resource-constrained and real-world settings.
32. Privacy-Preserving Object Detection & Localization Using Distributed Machine Learning: A Case Study of Infant Eyeblink Conditioning
Authors: Stefan Zwaard, Henk-Jan Boele, Hani Alers, Christos Strydis, Casey Lew-Williams, Zaid Al-Ars
Categories: cs.LG, cs.CR, cs.CV
Published: 2020-10-14
arXiv: 2010.07259v1
Abstract:
Distributed machine learning is becoming a popular model-training method due to privacy, computational scalability, and bandwidth capacities. In this work, we explore scalable distributed-training versions of two algorithms commonly used in object detection. A novel distributed training algorithm using Mean Weight Matrix Aggregation (MWMA) is proposed for Linear Support Vector Machine (L-SVM) object detection based in Histogram of Orientated Gradients (HOG). In addition, a novel Weighted Bin Aggregation (WBA) algorithm is proposed for distributed training of Ensemble of Regression Trees (ERT) landmark localization. Both algorithms do not restrict the location of model aggregation and allow custom architectures for model distribution. For this work, a Pool-Based Local Training and Aggregation (PBLTA) architecture for both algorithms is explored. The application of both algorithms in the medical field is examined using a paradigm from the fields of psychology and neuroscience - eyeblink conditioning with infants - where models need to be trained on facial images while protecting participant privacy. Using distributed learning, models can be trained without sending image data to other nodes. The custom software has been made available for public use on GitHub: https://github.com/SLWZwaard/DMT. Results show that the aggregation of models for the HOG algorithm using MWMA not only preserves the accuracy of the model but also allows for distributed learning with an accuracy increase of 0.9% compared with traditional learning. Furthermore, WBA allows for ERT model aggregation with an accuracy increase of 8% when compared to single-node models.
33. 2nd Place Solution to ECCV 2020 VIPriors Object Detection Challenge
Authors: Yinzheng Gu, Yihan Pan, Shizhe Chen
Categories: cs.CV
Published: 2020-07-17
arXiv: 2007.08849v1
Abstract:
In this report, we descibe our approach to the ECCV 2020 VIPriors Object Detection Challenge which took place from March to July in 2020. We show that by using state-of-the-art data augmentation strategies, model designs, and post-processing ensemble methods, it is possible to overcome the difficulty of data shortage and obtain competitive results. Notably, our overall detection system achieves 36.6$%$ AP on the COCO 2017 validation set using only 10K training images without any pre-training or transfer learning weights ranking us 2nd place in the challenge.
34. Learning Global Object-Centric Representations via Disentangled Slot Attention
Authors: Tonglin Chen, Yinxuan Huang, Zhimeng Shen, Jinghao Huang, Bin Li, Xiangyang Xue
Categories: cs.CV
Published: 2024-10-24
arXiv: 2410.18809v1
Abstract:
Humans can discern scene-independent features of objects across various environments, allowing them to swiftly identify objects amidst changing factors such as lighting, perspective, size, and position and imagine the complete images of the same object in diverse settings. Existing object-centric learning methods only extract scene-dependent object-centric representations, lacking the ability to identify the same object across scenes as humans. Moreover, some existing methods discard the individual object generation capabilities to handle complex scenes. This paper introduces a novel object-centric learning method to empower AI systems with human-like capabilities to identify objects across scenes and generate diverse scenes containing specific objects by learning a set of global object-centric representations. To learn the global object-centric representations that encapsulate globally invariant attributes of objects (i.e., the complete appearance and shape), this paper designs a Disentangled Slot Attention module to convert the scene features into scene-dependent attributes (such as scale, position and orientation) and scene-independent representations (i.e., appearance and shape). Experimental results substantiate the efficacy of the proposed method, demonstrating remarkable proficiency in global object-centric representation learning, object identification, scene generation with specific objects and scene decomposition.
35. Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight
Authors: Ming Sun, Haoxuan Dou, Junjie Yan
Categories: cs.CV
Published: 2021-05-19
arXiv: 2105.08994v1
Abstract:
Transfer learning can boost the performance on the targettask by leveraging the knowledge of the source domain. Recent worksin neural architecture search (NAS), especially one-shot NAS, can aidtransfer learning by establishing sufficient network search space. How-ever, existing NAS methods tend to approximate huge search spaces byexplicitly building giant super-networks with multiple sub-paths, anddiscard super-network weights after a child structure is found. Both thecharacteristics of existing approaches causes repetitive network trainingon source tasks in transfer learning. To remedy the above issues, we re-duce the super-network size by randomly dropping connection betweennetwork blocks while embedding a larger search space. Moreover, wereuse super-network weights to avoid redundant training by proposinga novel framework consisting of two modules, the neural architecturesearch module for architecture transfer and the neural weight searchmodule for weight transfer. These two modules conduct search on thetarget task based on a reduced super-networks, so we only need to trainonce on the source task. We experiment our framework on both MS-COCO and CUB-200 for the object detection and fine-grained imageclassification tasks, and show promising improvements with onlyO(CN)super-network complexity.
36. Evaluating the Single-Shot MultiBox Detector and YOLO Deep Learning Models for the Detection of Tomatoes in a Greenhouse
Authors: Sandro A. Magalhães, Luís Castro, Germano Moreira, Filipe N. Santos, mário Cunha, Jorge Dias, António P. Moreira
Categories: cs.CV, cs.RO
Published: 2021-09-02
arXiv: 2109.00810v1
Abstract:
The development of robotic solutions for agriculture requires advanced perception capabilities that can work reliably in any crop stage. For example, to automatise the tomato harvesting process in greenhouses, the visual perception system needs to detect the tomato in any life cycle stage (flower to the ripe tomato). The state-of-the-art for visual tomato detection focuses mainly on ripe tomato, which has a distinctive colour from the background. This paper contributes with an annotated visual dataset of green and reddish tomatoes. This kind of dataset is uncommon and not available for research purposes. This will enable further developments in edge artificial intelligence for in situ and in real-time visual tomato detection required for the development of harvesting robots. Considering this dataset, five deep learning models were selected, trained and benchmarked to detect green and reddish tomatoes grown in greenhouses. Considering our robotic platform specifications, only the Single-Shot MultiBox Detector (SSD) and YOLO architectures were considered. The results proved that the system can detect green and reddish tomatoes, even those occluded by leaves. SSD MobileNet v2 had the best performance when compared against SSD Inception v2, SSD ResNet 50, SSD ResNet 101 and YOLOv4 Tiny, reaching an F1-score of 66.15%, an mAP of 51.46% and an inference time of 16.44 ms with the NVIDIA Turing Architecture platform, an NVIDIA Tesla T4, with 12 GB. YOLOv4 Tiny also had impressive results, mainly concerning inferring times of about 5 ms.
37. Recent Trends in 2D Object Detection and Applications in Video Event Recognition
Authors: Prithwish Jana, Partha Pratim Mohanta
Categories: cs.CV
Published: 2022-02-07
arXiv: 2202.03206v1
Abstract:
Object detection serves as a significant step in improving performance of complex downstream computer vision tasks. It has been extensively studied for many years now and current state-of-the-art 2D object detection techniques proffer superlative results even in complex images. In this chapter, we discuss the geometry-based pioneering works in object detection, followed by the recent breakthroughs that employ deep learning. Some of these use a monolithic architecture that takes a RGB image as input and passes it to a feed-forward ConvNet or vision Transformer. These methods, thereby predict class-probability and bounding-box coordinates, all in a single unified pipeline. Two-stage architectures on the other hand, first generate region proposals and then feed it to a CNN to extract features and predict object category and bounding-box. We also elaborate upon the applications of object detection in video event recognition, to achieve better fine-grained video classification performance. Further, we highlight recent datasets for 2D object detection both in images and videos, and present a comparative performance summary of various state-of-the-art object detection techniques.
38. Spatial Transformer Network YOLO Model for Agricultural Object Detection
Authors: Yash Zambre, Ekdev Rajkitkul, Akshatha Mohan, Joshua Peeples
Categories: cs.CV, cs.AI, cs.LG
Published: 2024-07-31
arXiv: 2407.21652v2
Abstract:
Object detection plays a crucial role in the field of computer vision by autonomously locating and identifying objects of interest. The You Only Look Once (YOLO) model is an effective single-shot detector. However, YOLO faces challenges in cluttered or partially occluded scenes and can struggle with small, low-contrast objects. We propose a new method that integrates spatial transformer networks (STNs) into YOLO to improve performance. The proposed STN-YOLO aims to enhance the model’s effectiveness by focusing on important areas of the image and improving the spatial invariance of the model before the detection process. Our proposed method improved object detection performance both qualitatively and quantitatively. We explore the impact of different localization networks within the STN module as well as the robustness of the model across different spatial transformations. We apply the STN-YOLO on benchmark datasets for Agricultural object detection as well as a new dataset from a state-of-the-art plant phenotyping greenhouse facility. Our code and dataset are publicly available.
39. Object Detection with Multimodal Large Vision-Language Models: An In-depth Review
Authors: Ranjan Sapkota, Manoj Karkee
Categories: cs.CV, cs.AI, cs.CL
Published: 2025-08-25
arXiv: 2508.19294v2
Abstract:
The fusion of language and vision in large vision-language models (LVLMs) has revolutionized deep learning-based object detection by enhancing adaptability, contextual reasoning, and generalization beyond traditional architectures. This in-depth review presents a structured exploration of the state-of-the-art in LVLMs, systematically organized through a three-step research review process. First, we discuss the functioning of vision language models (VLMs) for object detection, describing how these models harness natural language processing (NLP) and computer vision (CV) techniques to revolutionize object detection and localization. We then explain the architectural innovations, training paradigms, and output flexibility of recent LVLMs for object detection, highlighting how they achieve advanced contextual understanding for object detection. The review thoroughly examines the approaches used in integration of visual and textual information, demonstrating the progress made in object detection using VLMs that facilitate more sophisticated object detection and localization strategies. This review presents comprehensive visualizations demonstrating LVLMs’ effectiveness in diverse scenarios including localization and segmentation, and then compares their real-time performance, adaptability, and complexity to traditional deep learning systems. Based on the review, its is expected that LVLMs will soon meet or surpass the performance of conventional methods in object detection. The review also identifies a few major limitations of the current LVLM modes, proposes solutions to address those challenges, and presents a clear roadmap for the future advancement in this field. We conclude, based on this study, that the recent advancement in LVLMs have made and will continue to make a transformative impact on object detection and robotic applications in the future.
40. Poly-YOLO: higher speed, more precise detection and instance segmentation for YOLOv3
Authors: Petr Hurtik, Vojtech Molek, Jan Hula, Marek Vajgl, Pavel Vlasanek, Tomas Nejezchleba
Categories: cs.CV, cs.LG, eess.IV
Published: 2020-05-27
arXiv: 2005.13243v2
Abstract:
We present a new version of YOLO with better performance and extended with instance segmentation called Poly-YOLO. Poly-YOLO builds on the original ideas of YOLOv3 and removes two of its weaknesses: a large amount of rewritten labels and inefficient distribution of anchors. Poly-YOLO reduces the issues by aggregating features from a light SE-Darknet-53 backbone with a hypercolumn technique, using stairstep upsampling, and produces a single scale output with high resolution. In comparison with YOLOv3, Poly-YOLO has only 60% of its trainable parameters but improves mAP by a relative 40%. We also present Poly-YOLO lite with fewer parameters and a lower output resolution. It has the same precision as YOLOv3, but it is three times smaller and twice as fast, thus suitable for embedded devices. Finally, Poly-YOLO performs instance segmentation using bounding polygons. The network is trained to detect size-independent polygons defined on a polar grid. Vertices of each polygon are being predicted with their confidence, and therefore Poly-YOLO produces polygons with a varying number of vertices.
41. Semi-Supervised Object Detection with Sparsely Annotated Dataset
Authors: Jihun Yoon, Seungbum Hong, Sanha Jeong, Min-Kook Choi
Categories: cs.CV
Published: 2020-06-21
arXiv: 2006.11692v1
Abstract:
In training object detector based on convolutional neural networks, selection of effective positive examples for training is an important factor. However, when training an anchor-based detectors with sparse annotations on an image, effort to find effective positive examples can hinder training performance. When using the anchor-based training for the ground truth bounding box to collect positive examples under given IoU, it is often possible to include objects from other classes in the current training class, or objects that are needed to be trained can only be sampled as negative examples. We used two approaches to solve this problem: 1) the use of an anchorless object detector and 2) a semi-supervised learning-based object detection using a single object tracker. The proposed technique performs single object tracking by using the sparsely annotated bounding box as an anchor in the temporal domain for successive frames. From the tracking results, dense annotations for training images were generated in an automated manner and used for training the object detector. We applied the proposed single object tracking-based semi-supervised learning to the Epic-Kitchens dataset. As a result, we were able to achieve \textbf{runner-up} performance in the Unseen section while achieving the first place in the Seen section of the Epic-Kitchens 2020 object detection challenge under IoU > 0.5 evaluation
42. Learning Object-Centric Video Models by Contrasting Sets
Authors: Sindy Löwe, Klaus Greff, Rico Jonschkowski, Alexey Dosovitskiy, Thomas Kipf
Categories: cs.CV, cs.LG
Published: 2020-11-20
arXiv: 2011.10287v1
Abstract:
Contrastive, self-supervised learning of object representations recently emerged as an attractive alternative to reconstruction-based training. Prior approaches focus on contrasting individual object representations (slots) against one another. However, a fundamental problem with this approach is that the overall contrastive loss is the same for (i) representing a different object in each slot, as it is for (ii) (re-)representing the same object in all slots. Thus, this objective does not inherently push towards the emergence of object-centric representations in the slots. We address this problem by introducing a global, set-based contrastive loss: instead of contrasting individual slot representations against one another, we aggregate the representations and contrast the joined sets against one another. Additionally, we introduce attention-based encoders to this contrastive setup which simplifies training and provides interpretable object masks. Our results on two synthetic video datasets suggest that this approach compares favorably against previous contrastive methods in terms of reconstruction, future prediction and object separation performance.
43. Teach YOLO to Remember: A Self-Distillation Approach for Continual Object Detection
Authors: Riccardo De Monte, Davide Dalle Pezze, Gian Antonio Susto
Categories: cs.CV
Published: 2025-03-06
arXiv: 2503.04688v1
Abstract:
Real-time object detectors like YOLO achieve exceptional performance when trained on large datasets for multiple epochs. However, in real-world scenarios where data arrives incrementally, neural networks suffer from catastrophic forgetting, leading to a loss of previously learned knowledge. To address this, prior research has explored strategies for Class Incremental Learning (CIL) in Continual Learning for Object Detection (CLOD), with most approaches focusing on two-stage object detectors. However, existing work suggests that Learning without Forgetting (LwF) may be ineffective for one-stage anchor-free detectors like YOLO due to noisy regression outputs, which risk transferring corrupted knowledge. In this work, we introduce YOLO LwF, a self-distillation approach tailored for YOLO-based continual object detection. We demonstrate that when coupled with a replay memory, YOLO LwF significantly mitigates forgetting. Compared to previous approaches, it achieves state-of-the-art performance, improving mAP by +2.1% and +2.9% on the VOC and COCO benchmarks, respectively.
44. Super Sparse 3D Object Detection
Authors: Lue Fan, Yuxue Yang, Feng Wang, Naiyan Wang, Zhaoxiang Zhang
Categories: cs.CV, cs.RO
Published: 2023-01-05
arXiv: 2301.02562v1
Abstract:
As the perception range of LiDAR expands, LiDAR-based 3D object detection contributes ever-increasingly to the long-range perception in autonomous driving. Mainstream 3D object detectors often build dense feature maps, where the cost is quadratic to the perception range, making them hardly scale up to the long-range settings. To enable efficient long-range detection, we first propose a fully sparse object detector termed FSD. FSD is built upon the general sparse voxel encoder and a novel sparse instance recognition (SIR) module. SIR groups the points into instances and applies highly-efficient instance-wise feature extraction. The instance-wise grouping sidesteps the issue of the center feature missing, which hinders the design of the fully sparse architecture. To further enjoy the benefit of fully sparse characteristic, we leverage temporal information to remove data redundancy and propose a super sparse detector named FSD++. FSD++ first generates residual points, which indicate the point changes between consecutive frames. The residual points, along with a few previous foreground points, form the super sparse input data, greatly reducing data redundancy and computational overhead. We comprehensively analyze our method on the large-scale Waymo Open Dataset, and state-of-the-art performance is reported. To showcase the superiority of our method in long-range detection, we also conduct experiments on Argoverse 2 Dataset, where the perception range ($200m$) is much larger than Waymo Open Dataset ($75m$). Code is open-sourced at https://github.com/tusen-ai/SST.
45. Correlation of Object Detection Performance with Visual Saliency and Depth Estimation
Authors: Matthias Bartolo, Dylan Seychell
Categories: cs.CV, cs.AI, cs.LG
Published: 2024-11-05
arXiv: 2411.02844v1
Abstract:
As object detection techniques continue to evolve, understanding their relationships with complementary visual tasks becomes crucial for optimising model architectures and computational resources. This paper investigates the correlations between object detection accuracy and two fundamental visual tasks: depth prediction and visual saliency prediction. Through comprehensive experiments using state-of-the-art models (DeepGaze IIE, Depth Anything, DPT-Large, and Itti’s model) on COCO and Pascal VOC datasets, we find that visual saliency shows consistently stronger correlations with object detection accuracy (mA$ρ$ up to 0.459 on Pascal VOC) compared to depth prediction (mA$ρ$ up to 0.283). Our analysis reveals significant variations in these correlations across object categories, with larger objects showing correlation values up to three times higher than smaller objects. These findings suggest incorporating visual saliency features into object detection architectures could be more beneficial than depth information, particularly for specific object categories. The observed category-specific variations also provide insights for targeted feature engineering and dataset design improvements, potentially leading to more efficient and accurate object detection systems.
46. Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation
Authors: Yongchao Feng, Yajie Liu, Shuai Yang, Wenrui Cai, Jinqing Zhang, Qiqi Zhan, Ziyue Huang, Hongxi Yan, Qiao Wan, Chenguang Liu, Junzhe Wang, Jiahui Lv, Ziqi Liu, Tengyuan Shi, Qingjie Liu, Yunhong Wang
Categories: cs.CV, cs.AI
Published: 2025-04-13
arXiv: 2504.09480v1
Abstract:
Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far been unevaluated. In this work, we present the systematic review of VLM-based detection and segmentation, view VLM as the foundational model and conduct comprehensive evaluations across multiple downstream tasks for the first time: 1) The evaluation spans eight detection scenarios (closed-set detection, domain adaptation, crowded objects, etc.) and eight segmentation scenarios (few-shot, open-world, small object, etc.), revealing distinct performance advantages and limitations of various VLM architectures across tasks. 2) As for detection tasks, we evaluate VLMs under three finetuning granularities: \textit{zero prediction}, \textit{visual fine-tuning}, and \textit{text prompt}, and further analyze how different finetuning strategies impact performance under varied task. 3) Based on empirical findings, we provide in-depth analysis of the correlations between task characteristics, model architectures, and training methodologies, offering insights for future VLM design. 4) We believe that this work shall be valuable to the pattern recognition experts working in the fields of computer vision, multimodal learning, and vision foundation models by introducing them to the problem, and familiarizing them with the current status of the progress while providing promising directions for future research. A project associated with this review and evaluation has been created at https://github.com/better-chao/perceptual_abilities_evaluation.
47. The Solution for CVPR2024 Foundational Few-Shot Object Detection Challenge
Authors: Hongpeng Pan, Shifeng Yi, Shouwei Yang, Lei Qi, Bing Hu, Yi Xu, Yang Yang
Categories: cs.CV
Published: 2024-06-18
arXiv: 2406.12225v1
Abstract:
This report introduces an enhanced method for the Foundational Few-Shot Object Detection (FSOD) task, leveraging the vision-language model (VLM) for object detection. However, on specific datasets, VLM may encounter the problem where the detected targets are misaligned with the target concepts of interest. This misalignment hinders the zero-shot performance of VLM and the application of fine-tuning methods based on pseudo-labels. To address this issue, we propose the VLM+ framework, which integrates the multimodal large language model (MM-LLM). Specifically, we use MM-LLM to generate a series of referential expressions for each category. Based on the VLM predictions and the given annotations, we select the best referential expression for each category by matching the maximum IoU. Subsequently, we use these referential expressions to generate pseudo-labels for all images in the training set and then combine them with the original labeled data to fine-tune the VLM. Additionally, we employ iterative pseudo-label generation and optimization to further enhance the performance of the VLM. Our approach achieve 32.56 mAP in the final test.
48. RGBT Salient Object Detection: A Large-scale Dataset and Benchmark
Authors: Zhengzheng Tu, Yan Ma, Zhun Li, Chenglong Li, Jieming Xu, Yongtao Liu
Categories: cs.CV
Published: 2020-07-07
arXiv: 2007.03262v6
Abstract:
Salient object detection in complex scenes and environments is a challenging research topic. Most works focus on RGB-based salient object detection, which limits its performance of real-life applications when confronted with adverse conditions such as dark environments and complex backgrounds. Taking advantage of RGB and thermal infrared images becomes a new research direction for detecting salient object in complex scenes recently, as thermal infrared spectrum imaging provides the complementary information and has been applied to many computer vision tasks. However, current research for RGBT salient object detection is limited by the lack of a large-scale dataset and comprehensive benchmark. This work contributes such a RGBT image dataset named VT5000, including 5000 spatially aligned RGBT image pairs with ground truth annotations. VT5000 has 11 challenges collected in different scenes and environments for exploring the robustness of algorithms. With this dataset, we propose a powerful baseline approach, which extracts multi-level features within each modality and aggregates these features of all modalities with the attention mechanism, for accurate RGBT salient object detection. Extensive experiments show that the proposed baseline approach outperforms the state-of-the-art methods on VT5000 dataset and other two public datasets. In addition, we carry out a comprehensive analysis of different algorithms of RGBT salient object detection on VT5000 dataset, and then make several valuable conclusions and provide some potential research directions for RGBT salient object detection.
49. Transfer learning in hybrid classical-quantum neural networks
Authors: Andrea Mari, Thomas R. Bromley, Josh Izaac, Maria Schuld, Nathan Killoran
Categories: quant-ph, cs.LG, stat.ML
Published: 2019-12-17
arXiv: 1912.08278v2
Abstract:
We extend the concept of transfer learning, widely applied in modern machine learning algorithms, to the emerging context of hybrid neural networks composed of classical and quantum elements. We propose different implementations of hybrid transfer learning, but we focus mainly on the paradigm in which a pre-trained classical network is modified and augmented by a final variational quantum circuit. This approach is particularly attractive in the current era of intermediate-scale quantum technology since it allows to optimally pre-process high dimensional data (e.g., images) with any state-of-the-art classical network and to embed a select set of highly informative features into a quantum processor. We present several proof-of-concept examples of the convenient application of quantum transfer learning for image recognition and quantum state classification. We use the cross-platform software library PennyLane to experimentally test a high-resolution image classifier with two different quantum computers, respectively provided by IBM and Rigetti.
50. A Hybrid Deep Learning Anomaly Detection Framework for Intrusion Detection
Authors: Rahul Kale, Zhi Lu, Kar Wai Fok, Vrizlynn L. L. Thing
Categories: cs.CR, cs.AI, cs.LG
Published: 2022-12-02
arXiv: 2212.00966v1
Abstract:
Cyber intrusion attacks that compromise the users’ critical and sensitive data are escalating in volume and intensity, especially with the growing connections between our daily life and the Internet. The large volume and high complexity of such intrusion attacks have impeded the effectiveness of most traditional defence techniques. While at the same time, the remarkable performance of the machine learning methods, especially deep learning, in computer vision, had garnered research interests from the cyber security community to further enhance and automate intrusion detections. However, the expensive data labeling and limitation of anomalous data make it challenging to train an intrusion detector in a fully supervised manner. Therefore, intrusion detection based on unsupervised anomaly detection is an important feature too. In this paper, we propose a three-stage deep learning anomaly detection based network intrusion attack detection framework. The framework comprises an integration of unsupervised (K-means clustering), semi-supervised (GANomaly) and supervised learning (CNN) algorithms. We then evaluated and showed the performance of our implemented framework on three benchmark datasets: NSL-KDD, CIC-IDS2018, and TON_IoT.