Weakly Supervised Object Detection Using Proposal- and Semantic-Level Relationships
The DOI matches its Crossref record; 56 of the 58 references it cites were found in a registry or an index.
Abstract
In recent years, weakly supervised object detection has attracted great attention in the computer vision community. Although numerous deep learning-based approaches have been proposed in the past few years, such an ill-posed problem is still challenging and the learning performance is still behind the expectation. In fact, most of the existing approaches only consider the visual appearance of each proposal region but ignore to make use of the helpful context information. To this end, this paper introduces two levels of context into the weakly supervised learning framework. The first one is the proposal-level context, i.e., the relationship of the spatially adjacent proposals. The second one is the semantic-level context, i.e., the relationship of the co-occurring object categories. Therefore, the proposed weakly supervised learning framework contains not only the cognition process on the visual appearance but also the reasoning process on the proposal- and semantic-level relationships, which leads to the novel deep multiple instance reasoning framework. Specifically, built upon a conventional CNN-based network architecture, the proposed framework is equipped with two additional graph convolutional network-based reasoning models to implement object location reasoning and multi-label reasoning within an end-to-end network training procedure. Comprehensive experiments on the widely used PASCAL VOC and MS COCO benchmarks have been implemented, which demonstrate the superior capacity of the proposed approach when compared with other state-of-the-art methods and baseline models.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Multi-instance learning is a group of supervised learning algorithms that has seen widespread application in WSOD [202-209].”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [206]
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Semi-supervised classification with graph convolutional networks
Kipf, T. N., & Welling, M. (2016) · arXiv · doi:10.48550/arxiv.1609.02907 · Cited by 24,853
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Selective Search for Object Recognition
Uijlings, J. R. R., van de Sande, K. E. A., Gevers, T., & Smeulders, A. W. M. (2013) · International Journal of Computer Vision · doi:10.1007/s11263-013-0620-5 · Cited by 5,980
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
Yan, S., Xiong, Y., & Lin, D. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12328 · Cited by 5,410
DeepGCNs: Can GCNs Go As Deep As CNNs?
Li, G., Muller, M., Thabet, A., & Ghanem, B. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00936 · Cited by 1,400
Multi-Label Image Recognition With Graph Convolutional Networks
Chen, Z.-M., Wei, X.-S., Wang, P., & Guo, Y. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00532 · Cited by 1,261
Exploring Visual Relationship for Image Captioning
Yao, T., Pan, Y., Li, Y., & Mei, T. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_42 · Cited by 870
Videos as Space-Time Region Graphs
Wang, X., & Gupta, A. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01228-1_25 · Cited by 765
Research works printed but not linked: 4
- 10.1109/CVPR.2016.311 · DOI · Paper page
- 10.1109/ICCV.2019.00662 · DOI
- Wei, TS2C: Tight box mining with surrounding segmentation context for weakly supervised object detection, 434
- 10.1109/CVPR.2019.00964 · DOI
Cited by
Object Detection in 20 Years: A Survey
Zou, Z., Chen, K., Shi, Z., Guo, Y., & Ye, J. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3238524 · Cited by 3,689
Towards Large-Scale Small Object Detection: Survey and Benchmarks
Cheng, G., Yuan, X., Yao, X., Yan, K., Zeng, Q., Xie, X., & Han, J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3290594 · Cited by 683
Self-citationDeep Industrial Image Anomaly Detection: A Survey
Liu, J., Xie, G., Wang, J., Li, S., Wang, C., Zheng, F., & Jin, Y. (2024) · Machine Intelligence Research · doi:10.1007/s11633-023-1459-z · Cited by 463
Yan, R., Qu, L., Wei, Q., Huang, S.-C., Shen, L., Rubin, D. L., Xing, L., & Zhou, Y. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3233574 · Cited by 183
“To address this issue, various approaches such as semisupervised and self-supervised learning methods [17], [18], [19], [20], [21], [22] have been proposed to allow models”
MethodThe evolution of object detection methods
Sun, Y., Sun, Z., & Chen, W. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108458 · Cited by 199
FedMix: Mixed Supervised Federated Learning for Medical Image Segmentation
Wicaksana, J., Yan, Z., Zhang, D., Huang, X., Wu, H., Yang, X. Y., & Cheng, K.-T. T. (2022) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2022.3233405 · Cited by 167
“To this end, efforts have been made to explore the use of some easily obtained image supervisions [43], [44] (e.”
BackgroundSelf-citationHybrid routing transformer for zero-shot learning
Cheng, D., Wang, G., Wang, B., Zhang, Q., Han, J., & Zhang, D. (2022) · Pattern Recognition · doi:10.1016/j.patcog.2022.109270 · Cited by 104
Self-citationReliable Mutual Distillation for Medical Image Segmentation Under Imperfect Annotations
Fang, C., Wang, Q., Cheng, L., Gao, Z., Pan, C., Cao, Z., Zheng, Z., & Zhang, D. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3237183 · Cited by 102
Self-citationYue, J., Fang, L., Ghamisi, P., Xie, W., Li, J., Chanussot, J., & Plaza, A. (2022) · IEEE Geoscience and Remote Sensing Magazine · doi:10.1109/mgrs.2022.3161377 · Cited by 93
“research [47], [48], [49], weakly supervised learning for RSI understanding usually needs to consider how to make full use of spatial and spectral features.”
BackgroundCamera Contrast Learning for Unsupervised Person Re-Identification
Zhang, G., Zhang, H., Lin, W., Chandran, A. K., & Jing, X. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3240001 · Cited by 84
“As only requiring unannotated training images, which can be readily obtained with object detection techniques [71], [72], they are easier to be deployed.”
MethodShadow-Consistent Semi-Supervised Learning for Prostate Ultrasound Segmentation
Xu, X., Sanford, T., Türkbey, B., Xu, S., Wood, B. J., & Yan, P. (2021) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2021.3139999 · Cited by 84
Wu, Z., Liu, C., Wen, J., Xu, Y. D., Yang, J. J., & Li, X. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3231744 · Cited by 76
“Since only some works have reported their results, here we compare with 14 methods, including PCL [23], MELM [36], CSC [45], WS-JDS [34], C-MIDN [30], WSOD 2 [19], PG-PS [24], PSLR [27], MIST [33], P-MIDN + MGSC [31], GradingNet-C-MIL [28], D-MIL [32], OICR [16] and OICR + Reg.”
BackgroundMethodÖztürk, C., Taşyürek, M., & Türkdamar, M. U. (2022) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.7542 · Cited by 76
Weakly supervised histopathology image segmentation with self-attention
Li, K., Qian, Z., Han, Y., Chang, E., Wei, B., Lai, M., Liao, J., Fan, Y., & Xu, Y. L. (2023) · Medical Image Analysis · doi:10.1016/j.media.2023.102791 · Cited by 86
Causal Reasoning Meets Visual Representation Learning: A Prospective Study
Liu, Y., Wei, Y.-S., Yan, H., Li, G., & Lin, L. (2022) · Machine Intelligence Research · doi:10.1007/s11633-022-1362-z · Cited by 83
“NExT-QA[215] Causal and temporal interactions 52K MC&OG Human ✓ ✓ ✓”
BackgroundInfluentialToward Label-Efficient Emotion and Sentiment Analysis
Zhao, S., Hong, X., Yang, J., Zhao, Y., & Ding, G. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3309299 · Cited by 76
GLFF: Global and Local Feature Fusion for AI-Synthesized Image Detection
Ju, Y., Jia, S., Cai, J., Guan, H., & Lyu, S. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3313503 · Cited by 78
“Feature Fusion: Numerous works, which rely on feature fusion, have been proposed for computer vision tasks, including semantic segmentation [53], [54], [55] and object detection [56], [57], [58], [59], [60].”
BackgroundProgressive Negative Enhancing Contrastive Learning for Image Dehazing and Beyond
Cheng, D., Li, Y., Zhang, D., Wang, N., Sun, J., & Gao, X. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3382493 · Cited by 50
Self-citationYu, C., Peng, B., Huang, Q., & Lei, J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3296583 · Cited by 49
“That is, there are certain dependencies among the generated proposals [19].”
BackgroundM-RRFS: A Memory-Based Robust Region Feature Synthesizer for Zero-Shot Object Detection
Huang, P., Zhang, D., Cheng, D., Han, L., Zhu, P., & Han, J. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02112-9 · Cited by 48
“ZSD task has received tremendous research interest in recent years (Rahman et al., 2018b; Bansal et al., 2018; Zhang et al., 2020b; Gupta et al., 2020; Li et al., 2019; Hayat et al., 2020; Zhao et al., 2020).”
Self-citationEnhanced Spatial Feature Learning for Weakly Supervised Object Detection
Wu, Z., Wen, J., Xu, Y. D., Yang, J. J., Li, X., & Zhang, D. D. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3178180 · Cited by 45
Self-citationClustering Aided Weakly Supervised Training to Detect Anomalous Events in Surveillance Videos
Zaheer, M. Z., Mahmood, A., Astrid, M., & Lee, S. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3274611 · Cited by 53
“Another related problem is object localization in weakly supervised settings [81], [82].”
BackgroundLearning Efficient and Adaptive Cross-Channel Dependencies for Weakly-Supervised Object Detection
Chen, P., Nie, X., Ning, Y., & Zhang, Y. (2025) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2025.3618564 · Cited by 53
Zhu, D., Du, B., Dong, Y., & Zhang, L. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3210389 · Cited by 37
Learning Constrained Dynamic Correlations in Spatiotemporal Graphs for Motion Prediction
Fu, J., Yang, F., Dang, Y., Liu, X., & Yin, J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3277476 · Cited by 51
“Explicitly modeling these two patterns with constrained dynamic correlation modeling can reduce the optimization difficulty and might inspire adjacency modeling for other graph-based visual learning tasks [54], [57], [58], [59], [60].”
BackgroundEquivalent Classification Mapping for Weakly Supervised Temporal Action Localization
Zhao, T., Han, J., Yang, L., & Zhang, D. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3178957 · Cited by 39
“Recently, weak supervision [31], [32], [33], [34] has received much attention from researchers.”
BackgroundSelf-citationFan, B., Yang, Y., Feng, W., Wu, F., Lu, J., & Liu, H. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3154165 · Cited by 39
Li, X., Wang, Z., Zhang, B., Sun, F., & Hu, X. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3237935 · Cited by 46
“Parts have been rarely used as auxiliaries or explicit intermediate representations of general object recognition models except in some few-shot learning settings [48], [49], [50].”
MethodNoise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data
Zhang, Z., Zhao, S., Jin, X., Xu, M., Yang, Y., Yan, S., & Wang, M. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3487361 · Cited by 47
“Recently, deep neural networks (DNNs) [28, 38, 50] have been successfully used for vari-1 ous high-level [26, 40, 44, 53] and low-level [43, 49, 52] vision tasks due to their strong learning abilities.”
Complementary Parts Contrastive Learning for Fine-Grained Weakly Supervised Object Co-Localization
Ma, L., Zhao, F., Hong, H.-Y., Wang, L., & Zhu, Y. (2023) · IEEE transactions on circuits and systems for video technology (Print) · doi:10.1109/tcsvt.2023.3265751 · Cited by 27
Generative Prompt Model for Weakly Supervised Object Localization
Zhao, Y., Ye, Q., Wu, W., Shen, C., & Wan, F. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00584 · Cited by 48
“CAM is also extended from WSOL to weakly supervised detection [12, 57, 70] and segmentation [10, 58, 63, 71].”
BackgroundLi, D., Zhang, H., Zhou, D., Shi, J., & Ma, J. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3274651 · Cited by 30
“In recent years, weakly-supervised learning has become an active research area in computer vision, and several meth-ods have been proposed for various vision tasks [49], [50], [51], [52].”
BackgroundUnsupervised Pre-Training With Language-Vision Prompts for Low-Data Instance Segmentation
Zhang, D., Li, H., He, D., Liu, N., Cheng, L., Wang, J., & Han, J. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3579469 · Cited by 54
Self-citationWan, Y., Zhong, Y., Ma, A., Wang, J., & Zhang, L. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3220699 · Cited by 32
“In some cases, it is faced with the lack or only a small part of labeled samples, which leads to the field of self-supervised learning [54], [55] and weak supervised learning [56], [57].”
BackgroundDiscriminative Suprasphere Embedding for Fine-Grained Visual Categorization
Ye, S., Peng, Q., Sun, W., Xu, J., Wang, Y., You, X., & Cheung, Y. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3202534 · Cited by 28
“Weakly supervised learning only uses label information, which can effectively avoid human subjective error [20], [21], [22], [23].”
BackgroundAugmented FCN: rethinking context modeling for semantic segmentation
Zhang, D., Zhang, L.-Y., & Tang, J.-H. (2023) · Science China Information Sciences · doi:10.1007/s11432-021-3590-1 · Cited by 30
Self-citationMisclassification in Weakly Supervised Object Detection
Wu, Z., Xu, Y. D., Yang, J. J., & Li, X. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3402981 · Cited by 31
“Following previous works [11], [31], we train the model on the training set and evaluate its performance on the validation set.”
BackgroundMethodInsulator Defect Detection Algorithm Based on Improved YOLOv11n
Zhao, J., Miao, S., Kang, R., Cao, L., Zhang, L., & Ren, Y. (2025) · Sensors · doi:10.3390/s25051327 · Cited by 30
Residual Tuning: Toward Novel Category Discovery Without Labels
Liu, Y., & Tuytelaars, T. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3140235 · Cited by 39
“In particular, an increasing number of weakly supervised object detection (WSOD) approaches [67], [68] have been proposed since many of the images are simply annotated with image-level labels without bounding box annotations.”
Vision-Based Detection and Classification of Used Electronic Parts
Chand, P., & Lal, S. P. (2022) · Sensors · doi:10.3390/s22239079 · Cited by 31
Learning Dual-Routing Capsule Graph Neural Network for Few-Shot Video Classification
Feng, Y., Gao, J., & Xu, C. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3156938 · Cited by 27
“[60] proposed a weakly supervised learning framework containing the cognition process on the visual appearance and the reasoning process on the”
BackgroundLiang, Y., Zhu, L., Wang, X., & Yang, Y. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3213563 · Cited by 26
“Inspired by some weakly supervised learning methods [19], [20], Huang and Li [21] introduce additional localization module to improve performances and interpret attention areas.”
MethodDynamic Viewing Pattern Analysis: Towards Large-Scale Screening of Children With ASD in Remote Areas
Xia, C., Zhang, D., Li, K., Li, H., Chen, M., Min, W., & Han, J. (2022) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2022.3223736 · Cited by 26
Self-citationWeakly Supervised Learning for Point Cloud Semantic Segmentation With Dual Teacher
Yao, B., Xiao, H., Zhuang, J., & Peng, C. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3304116 · Cited by 28
Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt
Li, H., Zhang, D., Liu, N., Cheng, L., Dai, Y., Zhang, C., Wang, X., & Han, J. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.01486 · Cited by 31
“In the future, we will follow more recent studies on visual saliency [24, 25, 39] for further promoting the prompt learning mechanism and apply the prompt learning mechanism to advance the weakly supervised learning community [38, 40, 42].”
BackgroundSelf-citationLiu, P., & Zheng, G. (2022) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2022.3162748 · Cited by 26
“There are other ways to quantify uncertainty as presented in [61], [63], [64].”
BackgroundForest Graph Convolutional Network for Surgical Action Triplet Recognition in Endoscopic Videos
Xi, N., Meng, J., & Yuan, J. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3191838 · Cited by 32
“Furthermore, deep multiple instance reasoning framework [73] is proposed to utilize graph convolutional network-based reasoning models to incorporate proposal-level context and semantic-level context into object localization reasoning and multi-label reasoning framework.”
MethodLearning an Invariant and Equivariant Network for Weakly Supervised Object Detection
Feng, X., Yao, X., Shen, H., Cheng, G., Xiao, B., & Han, J. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3275142 · Cited by 25
“Thus, some OICR-based approaches focused on exploring contextual information [23], [29], [32], [35], [36], or proposal optimization [37],”
BackgroundSelf-citationDai, Y., Zhao, K., Shen, L., Liu, S., Yan, X., & Li, Z. (2023) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2023.3279863 · Cited by 24
Qin, H., Xie, W., Li, Y., & Du, Q. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3298145 · Cited by 23
AD-Graph: Weakly Supervised Anomaly Detection Graph Neural Network
Ullah, W., Hussain, T., Ullah, F., Khan, M., Hassaballah, M., Rodrigues, J. J. P. C., Baik, S., & de Albuquerque, V. D. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/7868415 · Cited by 19
Cyclic Self-Training With Proposal Weight Modulation for Cross-Supervised Object Detection
Xu, Y., Zhou, C., Yu, X., & Yang, Y. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3261752 · Cited by 27
“Most prior works [7], [8], [9], [10], [11], [18], [19], [20], [21], [22], [23], [24], [25], [26], [27], [28], [29] formulate the weakly-supervised object detection (WSOD) task as a multiple instance learning (MIL) problem.”
RR-Net: Relation Reasoning for End-to-End Human-Object Interaction Detection
Yang, D., Zou, Y., Zhang, C., Cao, M., & Chen, J. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2021.3119892 · Cited by 28
“2) Appearance Attention and Graph Models: Inspired by attention mechanism [49]–[51] and relation networks [5], [6], [52]–[55] in action recognition [18], [56], recent researches focus on appearance attention [22], [23], [25], [31], [34], [57], [58] to improve HOI detection.”
MethodHeterogeneous Knowledge Network for Visual Dialog
Zhao, L., Li, J., Gao, L., Rao, Y., Song, J., & Shen, H. T. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3207228 · Cited by 21
Wang, G., Zhang, X., Peng, Z., Zhang, T., Tang, X., Zhou, H., & Jiao, L. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3395751 · Cited by 21
Zhuang, T., Qin, Z., Ding, Y., Qin, Z., Ji, G., Liu, Y., & Choo, K. R. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3491133 · Cited by 29
“Zhang et al. [26] developed a weakly supervised object detection approach that integrates proposal-level and semantic-level relationships, improving the detection performance under limited supervision.”
Mei, S., Cheng, J., He, X., Hu, H., & Wen, G. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3131908 · Cited by 22
Graph Representation Learning for Large-Scale Neuronal Morphological Analysis
Zhao, J., Chen, X., Xiong, Z., Zha, Z.-J., & Wu, F. H. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3204686 · Cited by 22
“In recent years, a lot of architectures for AGGREGATE and COMBINE have been proposed [28], [29], [30], [31], [32], [33], [34], [35], [36], [37], [38], [39].”
BackgroundCollaborative Contrastive Refining for Weakly Supervised Person Search
Jia, C., Luo, M., Yan, C., Zhu, L., Chang, X., & Zheng, Q. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3308393 · Cited by 18
“weakly supervised object detection [25], [26], a weakly supervised setting for person search [17], [18] is proposed to train a person search model only with bounding boxes.”
BackgroundCyclic-Bootstrap Labeling for Weakly Supervised Object Detection
Yin, Y., Deng, J., Zhou, W., Li, L., & Li, H. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00645 · Cited by 19
“Weakly supervised object detection (WSOD) [2, 18, 33, 32, 10, 29, 52, 41, 7, 20, 17, 34, 38, 1, 44, 37, 45, 49, 11, 22, 26, 4, 46, 47, 43, 50, 5, 51, 9, 28, 48, 16, 27, 21, 15, 31] has attracted much attention in recent years.”
BackgroundFI-WSOD: Foreground Information Guided Weakly Supervised Object Detection
Yin, Y., Deng, J., Zhou, W., Li, L., & Li, H. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3198018 · Cited by 18
“In the object detection area, weakly supervised object detection (WSOD) is of great interest in recent years [10], [11], [12], [13], [14], [15], [16], [17], [18], [19], [20], [21], [28], [29], [30], [31], [32].”
BackgroundSemantic Image Segmentation by Dynamic Discriminative Prototypes
Zhang, K., & Sato, Y. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3270637 · Cited by 19
“Zhang et al. [21] introduced two levels (proposal level and semantic level) of context into the weakly supervised learning framework and achieved great success in weakly supervised object detection.”
BackgroundBai, J., Ren, J., Xiao, Z. Q., Chen, Z., Gao, C., Ali, T. A. A., & Jiao, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3309889 · Cited by 19
“Zhang et al. [44] introduced two levels of context into the WSL framework to achieve superior WSOD performance.”
AugMoCrack: Augmented morphological attention network for weakly supervised crack detection
Hong, Y., Lee, S., & Yoo, S. B. (2022) · Electronics Letters · doi:10.1049/ell2.12562 · Cited by 17
Balanced One-Stage Object Detection by Enhancing the Effect of Positive Samples
Wang, Z., Zhu, W., Zhao, W., & Xu, L. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3237826 · Cited by 16
“Hence, our method can also be adopted to weakly supervised object detection [69], [70] or other special scenarios in object detection [71], [72] where our method can realize great potential in enhancing the role of positive samples.”
MethodWeakly Supervised Object Detection With Class Prototypical Network
Li, H., Li, Y., Cao, Y., Han, Y., Jin, Y., & Wei, Y. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3187257 · Cited by 14
“It inspires many works, which exploit context [17], [18], [20], segmentation maps [21]–[26], refinement modules [9], [14], [15] or other information [9], [27], [33] to refine the proposal scores of WS-DDN.”
BackgroundUncertainty-Aware Graph-Guided Weakly Supervised Object Detection
Zhu, Y., Zhang, Y., Ding, M., & Zuo, W. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3232487 · Cited by 15
“…supervised learning explores how to construct predictive models by learning with weak supervision, including weakly supervised object localization [34], [35], weakly supervised salience detection [36], [37], weakly supervised object detection [10], [11], [12], [13], [14], [15], [16], [17], etc. .”
BackgroundDual Context Network for real-time semantic segmentation
-, H. L. Y., Xie, W., Zhang, J., Zhang, Y., Zhu, W., Gao, J., Shao, Y., & Li, Y. (2023) · Machine Vision and Applications · doi:10.1007/s00138-023-01373-7 · Cited by 13
Co-Learning Meets Stitch-Up for Noisy Multi-Label Visual Recognition
Liang, C., Yang, Z., Zhu, L., & Yang, Y. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3270103 · Cited by 15
Explicit Local Coupling Global Structure Clustering
Li, H., Guo, Y., Ren, Z., Yu, F. R., You, J., & You, X. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3266283 · Cited by 12
“As an emerging and challenging problem in the computer vision community, weakly supervised learning is widely used for object localization and detection, and used for developing new generation computer vision systems and has received significant attention in the past decade [45].”
BackgroundWeakly Supervised Temporal Action Localization With Bidirectional Semantic Consistency Constraint
Li, G., Cheng, D., Ding, X., Wang, N., Li, J., & Gao, X. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3266062 · Cited by 14
“It is often useful to exploit the self-supervised learning strategy for learning better representation when we lack full supervision [40], [41].”
BackgroundJi, X., Liu, G.-P., & Cai, C. (2023) · Journal of Marine Science and Engineering · doi:10.3390/jmse11091733 · Cited by 15
Spatio-Temporal Deformable DETR for Weakly Supervised Defect Localization
Kim, Y.-M., Yoo, Y.-H., Yoon, I.-U., Myung, H., & Kim, J.-H. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3298777 · Cited by 12
Global Focal Learning for Semi-Supervised Oriented Object Detection
Wang, K., Xiao, Z., Wan, Q., Xia, F., Chen, P., & Li, D. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3438844 · Cited by 14
“Weakly-supervised methods [4], [5] aim at leveraging weak labels (like image labels), instead of precise labels or no labels.”
BackgroundDynamic sample weighting for weakly supervised object detection
Li, X., Song, Y., Zhang, R., Fu, X., Jiang, H., Wang, C., Liu, Z.-Q., Gao, J., Yu, J. X., Yu, M., et al. (2022) · Image and Vision Computing · doi:10.1016/j.imavis.2022.104444 · Cited by 10
Weakly Supervised Contrastive Learning for Unsupervised Vehicle Reidentification
Yu, J., Oh, H., Kim, M., & Kim, J. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3288139 · Cited by 9
“To tackle these issues, some approaches used weak supervisory signals such as camera and tracklet information [33], [34], [35], [36], [37], [38], [39] that can be obtained when collecting images to construct a dataset.”
MethodZhou, J., & Wu, Y. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3408034 · Cited by 13
“Furthermore, OPFA can be applied to image understanding tasks, such as object detection [64] and segmentation [65], by capturing spatial relationships between patch features and generating the anomaly score map to distinguish foreground from background.”
MethodForeign object debris detection in lane images using deep learning methodology
Selvaraj, P., Bhuvaneshwara Raja, K., T, K. T. T. K., Jagatheesaperumal, S. K., Alkhamees, B. F., & Hassan, M. M. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.2570 · Cited by 9
Dual Graph Inference Network for Weakly Supervised Semantic Segmentation
Zhang, J., Peng, B., & Wu, X. (2025) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2025.3544331 · Cited by 11
“The work by Zhang et al. [44] is similar to ours in that it also adopts a dual-branch graph reasoning strategy to capture rich contextual relationships in the image, thereby enhancing the robustness of weakly supervised learning.”
Robust Single Image Dehazing Based on Consistent and Contrast-Assisted Reconstruction
Cheng, D., Li, Y., Zhang, D., Wang, N., Gao, X., & Sun, J. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/119 · Cited by 9
Self-citationSemantic-Aware Dynamic Generation Networks for Few-Shot Human–Object Interaction Recognition
Ji, Z., An, P. N., Liu, X., Gao, C., Pang, Y., & Shao, L. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3263660 · Cited by 8
“Semantic knowledge is employed to alleviate the interference caused by the diversity of visual features in the same category and also provides a type of weakly supervised information [16], [17].”
BackgroundProposals Generation for Weakly Supervised Object Detection in Artwork Images
Milani, F., Vago, N. O. P., & Fraternali, P. (2022) · Journal of Imaging · doi:10.3390/jimaging8080215 · Cited by 9
“The authors of [39–41] leverage the power of CAMs as segmentation proposals, [42–45] introduce a collaboration loop between the segmentation and detection branches, [46] proposes a cascaded convolutional neural network and [47] exploit segmentation properties, i.e., purity and completeness, to…”
BackgroundCollaborative Learning-Based Network for Weakly Supervised Remote Sensing Object Detection
Chen, S., Wang, H., Mukherjee, M., & Xu, X. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3223845 · Cited by 7
Design of Bluetooth 5.1 Angle of Arrival Homing Controller for Autonomous Mobile Robot
Weinmann, K. J., & Simske, S. (2023) · Robotics · doi:10.3390/robotics12040115 · Cited by 8
Toward interpretable and generalized mitosis detection in digital pathology using deep learning
Farooq, H., Saleem, S., Aleem, I., Iftikhar, A., Sheikh, U., & Naveed, H. (2024) · Digital Health · doi:10.1177/20552076241255471 · Cited by 14
DeIoU: Toward Distinguishable Box Prediction in Densely Packed Object Detection
Wang, L., Zhan, Y., Lan, L., Lin, X., Tao, D., & Gao, X. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3415657 · Cited by 9
Compound Batch Normalization for Long-tailed Image Classification
Cheng, L., Fang, C., Zhang, D., Li, G., & Huang, G. (2022) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3503161.3547805 · Cited by 10
Self-citationTowards Weakly-Supervised Domain Adaptation for Lane Detection
Zhou, J., Zhang, C., & Beyerer, J. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00359 · Cited by 8
“Weakly supervised learning is used in several applications including object localization [6, 35], object detection [48, 58], semantic segmentation [4, 13, 20, 52].”
Weakly supervised collaborative localization learning method for sewer pipe defect detection
Yang, Y., Yang, S., Zhao, Q., Cao, H., & Peng, X. (2024) · Machine Vision and Applications · doi:10.1007/s00138-024-01587-3 · Cited by 6
“Zhang et al. [33] introduced the two-layer context relationship in the weakly supervised model to improve the awareness and reasoning process of visual appearance and learning.”
Research on Real-time Detection of Stacked Objects Based on Deep Learning
Geng, K., Qiao, J., Liu, N., Yang, Z., Zhang, R., & Li, H. (2023) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-023-02009-8 · Cited by 7
“Zhang et al. [90] incorporated two contextual levels into a weakly-supervised learning framework.”
Zhao, S., Zhang, Z., Wei, Y., Fan, J., Zhao, Y., Yan, S., & Wang, M. (2025) · Science China Information Sciences · doi:10.1007/s11432-023-4562-8 · Cited by 5
Cross-Domain Image-Object Retrieval Based on Weighted Optimal Transport
Hu, N., Huang, X., Li, W., Li, X., & Liu, A.-A. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3254889 · Cited by 7
Self-supervised sub-category exploration for Pseudo label generation
Chern, W., Kim, T., Nguyen, T., Asari, V. K., & Kim, H. (2023) · Automation in Construction · doi:10.1016/j.autcon.2023.104862 · Cited by 5
Shape description losses for medical image segmentation
Fang, X., Xu, X., Xia, J. J., Sanford, T., Türkbey, B., Xu, S., Wood, B. J., & Yan, P. (2023) · Machine Vision and Applications · doi:10.1007/s00138-023-01407-0 · Cited by 6
“In addition, other constraints, such as the semantic relationships betweenpixels,priorknowledge[9–11],havebeenintegrated with CNNs to implicitly constrain the shape of the target.”
BackgroundDisentangling Deep Network for Reconstructing 3D Object Shapes from Single 2D Images
Yang, Y., Han, J., Zhang, D., & Cheng, D. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88007-1_13 · Cited by 5
Self-citationAn Improved Point-Level Supervision Method for Temporal Action Localization
Lee, S.-J., Lim, J., Moon, J., & Jung, C. (2023) · IEEE Access · doi:10.1109/access.2023.3294572 · Cited by 4
AttentionPose: Attention-driven end-to-end model for precise 6D pose estimation
Rasheed, M. A., Farhan, R. N., & Jasim, W. M. (2023) · Journal of Intelligent Systems · doi:10.1515/jisys-2023-0153 · Cited by 4
Weakly-Supervised Video Object Grounding via Learning Uni-Modal Associations
Wang, W., Gao, J., & Xu, C. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3207581 · Cited by 5
“It is also noticed that there is another research line focusing on weakly-supervised video object localization and detection [37], [38], [39], where the target objects are predefined in a category list without any natural language description, which is different from our task.”
BackgroundDuan, H., Liu, Z., Wei, W., Zhang, T., Wang, J., Xu, L., Liu, H., & Chen, T. (2023) · Signal Processing Image Communication · doi:10.1016/j.image.2023.116968 · Cited by 4
Multi-level attention for referring expression comprehension
Sun, Y., Zhang, Y., Jiang, H., Hu, Y., & Yin, B. (2022) · Pattern Recognition Letters · doi:10.1016/j.patrec.2023.07.005 · Cited by 4
Metadata
- Authors
- Zhang, D., Zeng, W., Yao, J., & Han, J.
- Affiliations
- Northwestern Polytechnical University (CN)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2022-06-01
- Volume
- 44
- Issue
- 6
- Pages
- 3349-3363
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W3117854388
- Cited by
- 132
- References
- 58
- Citations by year
- 2026: 9 · 2025: 14 · 2024: 20 · 2023: 51 · 2022: 33
- FWCI
- 8.65
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Key R&D Program of Guangdong Province (2019B010110001)
- National Natural Science Foundation of China (61876140, U1801265)
- Research Funds for Interdisciplinary subject
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
- Keywords
- weakly supervised object detection, graph convolutional networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.