Humble Teachers Teach Better Students for Semi-Supervised Object Detection
Open accessThe DOI matches its Crossref record; 52 of the 52 references it cites were found in a registry or an index.
Abstract
We propose a semi-supervised approach for contemporary object detectors following the teacher-student dual model framework. Our method1is featured with 1) the exponential moving averaging strategy to update the teacher from the student online, 2) using plenty of region proposals and soft pseudo-labels as the student’s training targets, and 3) a light-weighted detection-specific data ensemble for the teacher to generate more reliable pseudo-labels. Compared to the recent state-of-the-art – STAC, which uses hard labels on sparsely selected hard pseudo samples, the teacher in our model exposes richer information to the student with soft-labels on many proposals. Our model achieves COCO-style AP of 53.04% on VOC07 val set, 8.4% better than STAC, when using VOC12 as unlabeled data. On MS-COCO, it outperforms prior work when only a small percentage of data is taken as labeled. It also reaches 53.8% AP on MS-COCO test-dev with 3.1% gain over the fully supervised ResNet-152 Cascaded R-CNN, by tapping into unlabeled data of a similar size to the labeled data.
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.
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
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 · cited 10×
“pre-training the detection network on the labeled data following standard training protocols [31].”
BackgroundMethodInfluentialImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“More specifically, we follow the MOCOv2 setup to pre-train the ResNet50 backbone in Faster R-CNN on each of the three unlabeled dataests: (1) MS-COCO unlabeled, (2) ImageNet1M [9] and (3) Instagram-1B [27].”
MethodYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
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
Rich 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
(2016) · Cited by 31,590
Feature Pyramid Networks for Object Detection
Lin, T.-Y., Dollar, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.106 · Cited by 30,939 · cited 2×
“We use Faster R-CNN with ResNet-50 backbone and FPN as our default base model.”
MethodGirshick, R. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.169 · Cited by 28,105
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128
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
Momentum Contrast for Unsupervised Visual Representation Learning
He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00975 · Cited by 13,347
A survey on Image Data Augmentation for Deep Learning
Shorten, C., & Khoshgoftaar, T. M. (2019) · Journal of Big Data · doi:10.1186/s40537-019-0197-0 · Cited by 13,203
A simple framework for contrastive learning of visual representations
Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020) · arXiv · doi:10.48550/arxiv.2002.05709 · Cited by 10,857
Cascade R-CNN: Delving into High Quality Object Detection
Cai, Z., & Vasconcelos, N. (2017) · arXiv · doi:10.48550/arxiv.1712.00726 · Cited by 7,408
Cascade R-CNN: Delving Into High Quality Object Detection
Cai, Z., & Vasconcelos, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00644 · Cited by 7,370
Stacked Hourglass Networks for Human Pose Estimation
Newell, A., Yang, K., & Deng, J. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46484-8_29 · Cited by 5,634
Tarvainen, A., & Valpola, H. (2017) · arXiv · doi:10.48550/arxiv.1703.01780 · Cited by 4,275
CornerNet: Detecting Objects as Paired Keypoints
Law, H., & Deng, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01264-9_45 · Cited by 3,852
FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence
Sohn, K., Berthelot, D., Li, C.-L., Zhang, Z., Carlini, N., Cubuk, E. D., Kurakin, A., Zhang, H., & Raffel, C. (2020) · arXiv · doi:10.48550/arxiv.2001.07685 · Cited by 2,892 · cited 11×
“FixMatch [39] and ReMixMatch [3] claim a data ensemble of random augmentations may hurt the teacher model performance, and is worse than weak augmentations (resizing and randomly flipping) applied to the inputs of the teacher.”
BackgroundMethodInfluentialImproved regularization of convolutional neural networks with cutout
DeVries, T., & Taylor, G. W. (2017) · arXiv · doi:10.48550/arxiv.1708.04552 · Cited by 2,776
Rokach, L. (2010) · Artificial Intelligence Review · doi:10.1007/s10462-009-9124-7 · Cited by 2,657
Self-Training With Noisy Student Improves ImageNet Classification
Xie, Q., Luong, M.-T., Hovy, E., & Le, Q. V. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01070 · Cited by 2,393
Unsupervised word sense disambiguation rivaling supervised methods
Yarowsky, D. (1995) · Proceedings of the 33rd annual meeting on Association for Computational Linguistics - · doi:10.3115/981658.981684 · Cited by 2,385
Improved Baselines with Momentum Contrastive Learning
Chen, X., Fan, H., Girshick, R., & He, K. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2003.04297 · Cited by 1,956 · cited 6×
“We also compare against supervised finetuning with pretrained MOCOv2 [7], a state-of-the-art contrastive learn- ing method for image classification pretraining.”
BackgroundMethodInfluentialCascaded Pyramid Network for Multi-person Pose Estimation
Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., & Sun, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00742 · Cited by 1,799
Learning from labeled and unlabeled data with label propagation
Zhu, X., & Ghahramani, Z. (2002) · Cited by 1,534
Unsupervised Data Augmentation for Consistency Training
Xie, Q., Dai, Z., Hovy, E., Luong, M.-T., & Le, Q. V. (2019) · arXiv · doi:10.48550/arxiv.1904.12848 · Cited by 1,517 · cited 2×
“The teacher and student model use asymmetric data augmentation – stronger augmentations for the student [46, 3, 39, 40] – to process different views of the same image [38].”
BackgroundAveraging Weights Leads to Wider Optima and Better Generalization
Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., & Wilson, A. G. (2018) · arXiv · doi:10.48550/arxiv.1803.05407 · Cited by 1,409
Temporal Ensembling for Semi-Supervised Learning
Laine, S., & Aila, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1610.02242 · Cited by 1,395
Exploring the Limits of Weakly Supervised Pretraining
Mahajan, D., Girshick, R., Ramanathan, V., He, K., Paluri, M., Li, Y., Bharambe, A., & van der Maaten, L. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01216-8_12 · Cited by 1,224
Integral Human Pose Regression
Sun, X., Xiao, B., Wei, F., Liang, S., & Wei, Y. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01231-1_33 · Cited by 874
Semi-Supervised Self-Training of Object Detection Models
Rosenberg, C., Hebert, M., & Schneiderman, H. (2005) · 2005 Seventh IEEE Workshops on Applications of Computer Vision (WACV/MOTION'05) - Volume 1 · doi:10.1109/acvmot.2005.107 · Cited by 796
S4L: Self-Supervised Semi-Supervised Learning
Zhai, X., Oliver, A., Kolesnikov, A., & Beyer, L. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00156 · Cited by 750 · cited 2×
“One dominant idea in this field is pseudo-labeling [39, 1, 23, 39, 4, 3, 49, 45] — pseudo-labels for unlabeled data are repeatedly generated by a pre-trained model, and the model is then updated by training on a mix of pseudo-labels and human annotated data.”
BackgroundMethodLabel Propagation for Deep Semi-Supervised Learning
Iscen, A., Tolias, G., Avrithis, Y., & Chum, O. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00521 · Cited by 686 · cited 1×
“Significant progress has been made in semi-supervised image classification [44, 4, 3, 51, 39, 21, 46, 17].”
BackgroundAutomatically generating extraction patterns from untagged text
Riloff, E. (1996) · Cited by 621
ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation AnchoringPreprint
Berthelot, D., Carlini, N., Cubuk, E. D., Kurakin, A., Sohn, K., Zhang, H., & Raffel, C. (2020) · arXiv (Cornell University) · Cited by 600
Consistency-based Semi-supervised Learning for Object detection
Jeong, J., Lee, S., Kim, J., & Kwak, N. (2019) · Seoul National University Open Repository (Seoul National University) · Cited by 545
Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning
Sajjadi, M. S. M., Javanmardi, M., & Taşdizen, T. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.04586 · Cited by 532
Probability of error of some adaptive pattern-recognition machines
Scudder, H. (1965) · IEEE Transactions on Information Theory · doi:10.1109/tit.1965.1053799 · Cited by 518
Data Distillation: Towards Omni-Supervised Learning
Radosavovic, I., Dollar, P., Girshick, R., Gkioxari, G., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00433 · Cited by 421
Rethinking Pre-training and Self-training
Zoph, B., Ghiasi, G., Lin, T.-Y., Cui, Y., Liu, H., Cubuk, E. D., & Le, Q. V. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.06882 · Cited by 369 · cited 1×
“Adopting ideas similar to those in semi-supervised image classification also leads to progress [52].”
A Simple Semi-Supervised Learning Framework for Object Detection
Sohn, K., Zhang, Z., Li, C., Zhang, H., Lee, C., & Pfister, T. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.04757 · Cited by 306
LSDA: Large Scale Detection Through Adaptation
Hoffman, J., Guadarrama, S., Tzeng, E., Hu, R., Donahue, J., Girshick, R., Darrell, T., & Saenko, K. (2014) · arXiv · doi:10.48550/arxiv.1407.5035 · Cited by 284
Zhang, Y., Sohn, K., Villegas, R., Pan, G., & Lee, H. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298621 · Cited by 216 · cited 1×
“Such guidance has been shown to be helpful for localization [50].”
BackgroundSelf-citationLarge Scale Semi-Supervised Object Detection Using Visual and Semantic Knowledge Transfer
Tang, Y., Wang, J., Gao, B., Dellandrea, E., Gaizauskas, R., & Chen, L. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.233 · Cited by 136
Self-citationTowards Human-Machine Cooperation: Self-Supervised Sample Mining for Object Detection
Wang, K., Yan, X., Zhang, D., Zhang, L., & Lin, L. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00173 · Cited by 127
Proposal Learning for Semi-Supervised Object Detection
Tang, P., Ramaiah, C., Wang, Y., Xu, R., & Xiong, C. (2021) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv48630.2021.00234 · Cited by 123 · cited 1×
“3), and significantly outperforms other self-supervised methods such as Proposal Learning [42], CSD [19] and STAC [40].”
MethodNOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection
Gao, J., Wang, J., Dai, S., Li, L.-J., & Nevatia, R. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00960 · Cited by 112
Learning Robust Facial Landmark Detection via Hierarchical Structured Ensemble
Zou, X., Zhong, S., Yan, L., Zhao, X., Zhou, J., & Wu, Y. N. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00023 · Cited by 92
Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learning
Arazo, E., Ortego, D., Albert, P., O'Connor, N. E., & McGuinness, K. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207304 · Cited by 77
Interpolation-based Semi-supervised Learning for Object Detection
Jeong, J., Verma, V., Hyun, M., Kannala, J., & Kwak, N. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.01143 · Cited by 66
Cited by
Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection
Elezi, I., Yu, Z., Anandkumar, A., Leal-Taixe, L., & Alvarez, J. M. (2021) · arXiv · Cited by 50
Metadata
- Authors
- Tang, Y., Chen, W., Luo, Y., & Zhang, Y.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 3131-3140
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3158661000
- Cited by
- 196
- References
- 52
- FWCI
- 12.13
- Type
- conference paper
- Language
- en
- Open access
- green
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.