Self Paced Deep Learning for Weakly Supervised Object Detection
Open accessThe DOI matches its Crossref record; 48 of the 49 references it cites were found in a registry or an index.
Abstract
In a weakly-supervised scenario object detectors need to be trained using image-level annotation alone. Since bounding-box-level ground truth is not available, most of the solutions proposed so far are based on an iterative, Multiple Instance Learning framework in which the current classifier is used to select the highest-confidence boxes in each image, which are treated as pseudo-ground truth in the next training iteration. However, the errors of an immature classifier can make the process drift, usually introducing many of false positives in the training dataset. To alleviate this problem, we propose in this paper a training protocol based on the self-paced learning paradigm. The main idea is to iteratively select a subset of images and boxes that are the most reliable, and use them for training. While in the past few years similar strategies have been adopted for SVMs and other classifiers, we are the first showing that a self-paced approach can be used with deep-network-based classifiers in an end-to-end training pipeline. The method we propose is built on the fully-supervised Fast-RCNN architecture and can be applied to similar architectures which represent the input image as a bag of boxes. We show state-of-the-art results on Pascal VOC 2007, Pascal VOC 2010 and ILSVRC 2013. On ILSVRC 2013 our results based on a low-capacity AlexNet network outperform even those weakly-supervised approaches which are based on much higher-capacity networks.
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
“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 [208]
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
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
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 2×
“The ILSVRC 2013 detection dataset [38] is a standard benchmark for object detection.”
MethodRich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014) · 2014 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2014.81 · Cited by 32,684
He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Girshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599
FaceNet: A unified embedding for face recognition and clustering
Schroff, F., Kalenichenko, D., & Philbin, J. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298682 · Cited by 15,267 · cited 1×
“, hard-negative mining) can be useful in a supervised scenario [18], [19].”
BackgroundSelective 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
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 2×
“A pioneering work in this direction is the curriculum learning approach proposed in [11].”
Background
Research works printed but not linked: 2
- [15] K. He, G. Gkioxari, P. Doll´ ar, and R. B. Girshick. Mask R-CNN. In ICCV , 2017. -
- [39] J. S. Supancic III and D. Ramanan. Self-paced learning for longterm tracking. In CVPR , pages 2379-2386, 2013. -
Cited by
Items 101–135 of 135
2019 Index IEEE Transactions on Pattern Analysis and Machine Intelligence Vol. 41
(2019) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2953823 · Cited by 3
Low-Budget Label Query through Domain Alignment EnforcementPreprint
Almeida, J., Saltori, C., Rota, P., & Sebe, N. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.00238 · Cited by 3
Self-citationSuhas, M., Abisset‐Chavanne, E., & Rey, P.-A. (2025) · Applied Sciences · doi:10.3390/app152111532 · Cited by 2
RMSOD: A RetinaNet based Mixed Supervised Object Detection Framework
Bastian, B. T., & Jiji, C. V. (2022) · IEEE India Conference · doi:10.1109/indicon56171.2022.10039939 · Cited by 2
Learning 3D Perception from Others' Predictions
Yoo, J., Feng, Z., Pan, T.-Y., Sun, Y., Phoo, C. P., Chen, X., Campbell, M., Weinberger, K. Q., Hariharan, B., & Chao, W. (2024) · International Conference on Learning Representations · doi:10.48550/arxiv.2410.02646 · Cited by 2
Deep Learning and Binocular Stereovision to Achieve Fast Detection and Location of Target
Wang, Q., Liang, Y., Wang, Z., Li, W., Jiang, Z., & Zhao, Y. (2019) · Lecture notes in electrical engineering · doi:10.1007/978-981-32-9686-2_36 · Cited by 2
Activity and Relationship Modeling Driven Weakly Supervised Object Detection
Li, Y., Qian, Y., Xu, Y., & Zhang, Y. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412697 · Cited by 2
RAVANBAKHSH, S. M. (2019) · arXiv (Cornell University) · doi:10.15167/ravanbakhsh-sayyed-mahdyar_phd2019-02-25 · Cited by 2
Hierarchy of GANs for learning embodied self-awareness modelPreprint
Ravanbakhsh, M., Baydoun, M., Campo, D., Marin-Plaza, P., Martín, D., Marcenaro, L., & Regazzoni, C. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.04012 · Cited by 2
Reyes-Cocoletzi, L., Olmos-Pineda, I., & Olvera-López, J. A. (2019) · Research in Computing Science · doi:10.13053/rcs-148-9-5 · Cited by 1
Analysis of Classroom Teaching Status Based on Target Detection Model
Wang, B., & Guo, X. J. (2019) · IEEE International Conference on Software Engineering and Service Science (ICSESS) · doi:10.1109/icsess47205.2019.9040790 · Cited by 1
Mutual Constraint Learning for Weakly Supervised Object Detection
Liu, Y., Chen, W., Mahmud, S. M. H., Qu, H., Miao, K., Feng, W. Q., & Zhang, Z. (2019) · International Conference on Intelligent Systems and Knowledge Engineering (ISKE) · doi:10.1109/iske47853.2019.9170207 · Cited by 1
Improvising Weakly Supervised Object Detection WSOD using Deep Learning Technique
Wadmare, J. G., & Patil, S. (2020) · International Journal of Engineering and Advanced Technology · doi:10.35940/ijeat.b3796.029320 · Cited by 1
Cluster-based Curriculum Learning for Vision-and-Language Navigation
Wang, T., Wu, Z., Liu, Z., & Wang, D. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892100 · Cited by 1
Self-Paced Probabilistic Principal Component Analysis for Data with OutliersPreprint
Zhao, B., Xiao, X., Zhang, W., Zhang, B., & Xia, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.06546 · Cited by 1
Low-Shot Learning from Imaginary 3D ModelPreprint
Pahde, F., Puscas, M., Wolff, J., Klein, T., Sebe, N., & Nabi, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.01868 · Cited by 1
Self-citationWeakly-Supervised Semantic Segmentation of Circular-Scan, Synthetic-Aperture-Sonar ImageryPreprint
Sledge, I. J., Byrne, D. M., King, J. L., Ostertag, S. H., Woods, D., Prater, J. L., Kennedy, J. L., Marston, T. M., & Príncipe, J. C. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2401.11313 · Cited by 1
Класифікація гістологічних зображень раку простати
Ілюшик, Т. С. (2021) · Електронний архів наукових та освітніх матеріалів КПІ ім. Ігоря Сікорського (КПІ ім. Ігоря Сікорського) · Cited by 1
Weakly Supervised Object Localization Using Self-Paced Pyramid Adversarial Learning
Pan, F.-C., Bian, B., Wang, B., Yang, Y., & Ju, X. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207099
Sahoo, S. K. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-16-8512-5_34
Mercadier, M. (2022) · WORLD SCIENTIFIC eBooks · doi:10.1142/9789811260483_0003
Learning from limited labelled data: contributions to weak, few-shot, and unsupervised learning
Rodríguez, J. J. S. (2022) · RiuNet (Universitat Politècnica de València) · doi:10.4995/thesis/10251/190633
Explain what you see: argumentation-based learning and robotic vision
Ayoobi, H. (2023) · University of Groningen research database (University of Groningen / Centre for Information Technology) · doi:10.33612/diss.506782323
Liu, Y., & Zhang, L. (2023) · Proceedings - International Conference on Image Processing · doi:10.1109/icip49359.2023.10222789
Ma, Z., Fan, Y., Luo, W., Wang, C.-L., Zhou, L., Wang, D., & Duan, Y.-Q. (2024) · Springer series in geomechanics and geoengineering · doi:10.1007/978-981-97-0272-5_29
Zhu, L., Jiang, X., Shen, F., Wang, G., Yang, Y., & Xu, X. (2024) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme57554.2024.10687638
Active Learning Application for Mitosis Detection. A Brief Review.
Ferreira-Leite, M., Gonzalez, D. G., Magalhães, L., & Cunha, A. M. T. D. S. (2025) · Procedia Computer Science · doi:10.1016/j.procs.2025.02.220
TikogAI: A Feature-Engineered CNN Model for Classifying Indigenous Tikog Leaves in Banig Weaving
Caluza, L. J. B., & Fajardo, A. C. (2025) · Journal of Innovative Image Processing · doi:10.36548/jiip.2025.2.006
Caluza, L. J. B., & Fajardo, A. C. (2025) · International Conference on Control Systems and Computer Science · doi:10.1109/cscs66924.2025.00042
Laguna Queirolo, R. J. (2025) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas)
ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object DetectionPreprint
Bernardi, M., Cappellino, C., Mosconi, M., Sangineto, E., Porrello, A., & Calderara, S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.12409
Self-citationIndicateurs de risques bancaires, apprentissage machine et inégalités de concentration unilatérales
Mercadier, M. (2020) · theses.fr (ABES) · doi:10.70675/401dc78dz6c13z4736zbf3fzb7b7cd895ca3
Modèles de comportement et loi de défaillance de systèmes enrichis par les données
Suhas, M. (2024) · theses.fr (ABES) · doi:10.70675/798980bfz6736z4376z97a4z8533e0af90c1
Customized Text-to-Image Generation With Curriculum Multi-Reward Reinforcement Learning
Zhou, Y., Wang, X., Chen, H., Zhang, Y. J., & Zhu, W. (2026) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2026.3705898
Learning Object Detection with Weak Supervision
Xu, Y. (2023) · OPUS - Open Publications of UTS Scholars (University of Technology Sydney)
Metadata
- Authors
- Sangineto, E., Nabi, M., Culibrk, D., & Sebe, N.
- Affiliations
- University of Trento (IT)
- Systems, Applications & Products in Data Processing (Germany) (DE)
- University of Novi Sad (RS)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2019-03-01
- Volume
- 41
- Issue
- 3
- Pages
- 712-725
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- 1939-3539
- OpenAlex
- W2494236530
- Cited by
- 114
- References
- 49
- Citations by year
- 2025: 6 · 2024: 9 · 2023: 12 · 2022: 14 · 2021: 16 · 2020: 21 · 2019: 25
- FWCI
- 8.63
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Iris (University of Trento) (submittedVersion, other-oa)
- IRIS UNIMORE (University of Modena and Reggio Emilia) (submittedVersion, cc-by)
- arXiv (Cornell University)
- Funders
- Nvidia
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
- Keywords
- weakly supervised object detection, self-paced learning, image-level annotations, multiple instance learning, pseudo-labeling, training data selection, Fast R-CNN, AlexNet, Pascal VOC
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.