Papers › End-to-End Semi-Supervised Object Detection with Soft Teacher

End-to-End Semi-Supervised Object Detection with Soft Teacher

16 Jun 2021ICCV 2021 10arXiv:2106.09018archive 2025-07-28

Mengde Xu, Zheng Zhang, Han Hu, JianFeng Wang, Lijuan Wang, Fangyun Wei, Xiang Bai, Zicheng Liu

This paper presents an end-to-end semi-supervised object detection approach, in contrast to previous more complex multi-stage methods. The end-to-end training gradually improves pseudo label qualities during the curriculum, and the more and more accurate pseudo labels in turn benefit object detection training. We also propose two simple yet effective techniques within this framework: a soft teacher mechanism where the classification loss of each unlabeled bounding box is weighed by the classification score produced by the teacher network; a box jittering approach to select reliable pseudo boxes for the learning of box regression. On the COCO benchmark, the proposed approach outperforms previous methods by a large margin under various labeling ratios, i.e. 1\%, 5\% and 10\%. Moreover, our approach proves to perform also well when the amount of labeled data is relatively large. For example, it can improve a 40.9 mAP baseline detector trained using the full COCO training set by +3.6 mAP, reaching 44.5 mAP, by leveraging the 123K unlabeled images of COCO. On the state-of-the-art Swin Transformer based object detector (58.9 mAP on test-dev), it can still significantly improve the detection accuracy by +1.5 mAP, reaching 60.4 mAP, and improve the instance segmentation accuracy by +1.2 mAP, reaching 52.4 mAP. Further incorporating with the Object365 pre-trained model, the detection accuracy reaches 61.3 mAP and the instance segmentation accuracy reaches 53.0 mAP, pushing the new state-of-the-art.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

microsoft/SoftTeacher officialmentioned in papermentioned on GitHubpytorchMIT report
JCZ404/Semi-DETR mentioned on GitHubpytorchMIT report
amazon-research/bigdetection mentioned on GitHubpytorchApache-2.0 report
amazon-science/bigdetection mentioned on GitHubpytorchApache-2.0 report
hattrickcr7/SoftTeacher mentioned on GitHubpytorch report
hik-lab/ssod mentioned on GitHubpytorchApache-2.0 report
hikvision-research/SSOD mentioned on GitHubpytorchApache-2.0 report
lexisnexis-risk-open-source/ledetection mentioned on GitHubpytorchApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Instance SegmentationObject DetectionPseudo LabelSemantic SegmentationSemi-Supervised Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation COCO minival Soft Teacher + Swin-L(HTC++, multi-scale) mask AP 52.5 #13 of 93 Archive leaderboard report
Instance Segmentation COCO minival Soft Teacher + Swin-L(HTC++, single-scale) mask AP 51.9 #17 of 93 Archive leaderboard report
Instance Segmentation COCO test-dev Soft Teacher + Swin-L (HTC++, multi-scale) mask AP 53.0 #12 of 112 Archive leaderboard report
Object Detection COCO minival Soft Teacher + Swin-L (HTC++, multi-scale) box AP 60.7 #20 of 220 Archive leaderboard report
Object Detection COCO minival Soft Teacher+Swin-L(HTC++, single scale) box AP 60.1 #27 of 220 Archive leaderboard report
Object Detection COCO test-dev Soft Teacher + Swin-L (HTC++, multi-scale) box mAP 61.3 #24 of 225 Archive leaderboard report
Semi-Supervised Object Detection COCO 1% labeled data Soft Teacher + Swin-L(HTC++, multi-scale) mAP 20.46 #16 of 22 Archive leaderboard report
Semi-Supervised Object Detection COCO 10% labeled data Soft Teacher detector FasterRCNN-Res50 #17 of 27 Archive leaderboard report
Semi-Supervised Object Detection COCO 10% labeled data Soft Teacher mAP 34.04 #17 of 27 Archive leaderboard report
Semi-Supervised Object Detection COCO 100% labeled data Soft Teacher mAP 44.9 #6 of 13 Archive leaderboard report
Semi-Supervised Object Detection COCO 5% labeled data Soft Teacher + Swin-L(HTC++, multi-scale) mAP 30.74 #14 of 23 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxStochastic DepthSwin TransformerTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections