Weakly Supervised Object Localization and Detection: A Survey
Open accessThe DOI matches its Crossref record; 217 of the 217 references it cites were found in a registry or an index.
Abstract
As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received significant attention in the past decade. As methods have been proposed, a comprehensive survey of these topics is of great importance. In this work, we review (1) classic models, (2) approaches with feature representations from off-the-shelf deep networks, (3) approaches solely based on deep learning, and (4) publicly available datasets and standard evaluation metrics that are widely used in this field. We also discuss the key challenges in this field, development history of this field, advantages/disadvantages of the methods in each category, the relationships between methods in different categories, applications of the weakly supervised object localization and detection methods, and potential future directions to further promote the development of this research field.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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?
The cited source says what the claim attributes to it.
In the citing paper
“Weakly Supervised Object Detection (WSOD) aims at easing the reliance on data annotation by training a detector with only image-level annotations instead of bounding boxes [201].”
From Object Detection in 20 Years: A Survey (2023) · cites this paper as [201]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Items 201–217 of 217
Learning to Find Common Objects Across Few Image Collections
Shaban, A., Rahimi, A. M., Bansal, S., Gould, S. J., Boots, B., & Hartley, R. I. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00522 · Cited by 8
Fusing generic objectness and deformable part-based models for weakly supervised object detection
Tang, Y., Wang, X., Dellandréa, E., Masnou, S., & Chen, L. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025827 · Cited by 7
Optimizing Region Selection for Weakly Supervised Object DetectionPreprint
Jiang, W., Ngo, T., Manjunath, B. S., Zhao, Z., & Su, F. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.01723 · Cited by 6
Sparse weakly supervised models for object localization in road environment
Zadrija, V., Krapac, J., Šegvić, S., & Verbeek, J. J. (2018) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2018.10.004 · Cited by 6
Dual-attention Focused Module for Weakly Supervised Object LocalizationPreprint
Zhou, Y., Chen, Z., Shen, H., Liu, Q., Zhao, R., & Liang, Y. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.04813 · Cited by 6
Weakly Supervised Object Localization with Large Fisher Vectors
Krapac, J., & Šegvić, S. (2015) · International Conference on Computer Vision Theory and Applications · doi:10.5220/0005294900440053 · Cited by 5
Hsu, C.-Y., & Li, W. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.04009 · Cited by 5
Weakly-supervised multi-class object detection using multi-type 3D features
Kanezaki, A., Kuniyoshi, Y., & Harada, T. (2013) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2502081.2502159 · Cited by 4
Adapting Object Detectors from Images to Weakly Labeled Videos
Chanda, O., Teh, E. W., Rochan, M., Guo, Z., & Wang, Y. (2017) · British Machine Vision Conference (BMVC) · doi:10.5244/c.31.56 · Cited by 4
Zhang, M., & Zeng, B. (2020) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2020.102903 · Cited by 4
Hsu, C.-Y., & Li, W. (2020) · British Machine Vision Conference (BMVC) · doi:10.5244/c.34.145 · Cited by 4
Patch-Level Spatial Layout for Classification and Weakly Supervised Localization
Zadrija, V., Krapac, J., Verbeek, J. J., & Šegvić, S. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24947-6_41 · Cited by 3
Object co-detection via low-rank and sparse representation dictionary learning
Xie, Y., Huang, C., Song, T., Ma, J., & Jing, J. (2013) · Visual Communications and Image Processing · doi:10.1109/vcip.2013.6706361 · Cited by 3
Weakly supervised object detection with correlation and part suppression
Wan, F., Wei, P., Han, Z., Fu, K., & Ye, Q. (2016) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2016.7533038 · Cited by 3
Window mining by clustering mid-level representation for weakly supervised object detection
Wang, C., Ren, W., & Huang, K. (2014) · Proceedings - International Conference on Image Processing · doi:10.1109/icip.2014.7025826 · Cited by 2
From Weakly Supervised Object Localization to Semantic Segmentation by Probabilistic Image Modeling
Wilhelm, T., Grzeszick, R., Fink, G. A., & Woehler, C. (2017) · International Conference on Digital Image Computing: Techniques and Applications (DICTA) · doi:10.1109/dicta.2017.8227436 · Cited by 2
Patch-wise Weakly Supervised Learning for Object Localization in Video
Huh, D., Kim, T., & Kim, J. (2019) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic.2019.8668987 · Cited by 2
Research works printed but not linked: 7
- Chen, Learning efficient object detection models with knowledge distillation,, 742
- Khan, Learning object detectors from weakly-labeled internet images, Proc. 35th OAGM/AAPR Workshop, 326
- 10.5555/2999134.2999257 · doi:10.5555/2999134.2999257
- 10.1109/cvpr42600.2020.00879 · DOI
- 10.5244/c.26.78 · DOI · Paper page
- Wei, TS2C: Tight box mining with surrounding segmentation context for weakly supervised object detection,, 434
- [197] C.-L. Zhang, Y.-H. Cao, and J. Wu. Rethinking the route towards weakly supervised object localization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , June 2020. 9 · 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
“Weakly supervised object detection (WSOD) aims at easing the reliance on data annotation by training a detector with only image-level annotations instead of bounding boxes [201].”
Manakitsa, N., Maraslidis, G. S., Moysis, L., & Fragulis, G. F. (2024) · Technologies · doi:10.3390/technologies12020015 · Cited by 286
Computer vision framework for crack detection of civil infrastructure—A review
Ai, D., Jiang, G., Lam, S.-K., He, P., & Li, C. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105478 · Cited by 297
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
Few-Shot Object Detection: A Comprehensive Survey
Köhler, M., Eisenbach, M., & Groß, H. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3265051 · Cited by 196
Metadata
- Authors
- Zhang, D., Han, J., Cheng, G., & Yang, M.-H.
- Affiliations
- Xidian University (CN)
- Northwestern Polytechnical University (CN)
- University of California, Merced (US)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2021
- Volume
- 44
- Issue
- 9
- Pages
- 1-1
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W3152635971
- Cited by
- 277
- References
- 217
- Citations by year
- 2026: 11 · 2025: 34 · 2024: 74 · 2023: 79 · 2022: 60 · 2021: 19
- FWCI
- 3.61
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- National Science Foundation (1149783, CAREER)
- National Natural Science Foundation of China (61773301, 61876140, 2017YFB1002201)
- 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 localization, weakly supervised object detection, object localization, object detection, deep learning, feature representation, benchmark dataset, evaluation metrics, computer vision applications
- MeSH terms
- Algorithms, Artificial Intelligence, Neural Networks, Computer
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.