Papers › Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised...

Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection

4 Sep 2022CVPR 2023 1arXiv:2209.01589archive 2025-07-28

Xinjiang Wang, Xingyi Yang, Shilong Zhang, Yijiang Li, Litong Feng, Shijie Fang, Chengqi Lyu, Kai Chen, Wayne Zhang

In this study, we dive deep into the inconsistency of pseudo targets in semi-supervised object detection (SSOD). Our core observation is that the oscillating pseudo-targets undermine the training of an accurate detector. It injects noise into the student's training, leading to severe overfitting problems. Therefore, we propose a systematic solution, termed ConsistentTeacher, to reduce the inconsistency. First, adaptive anchor assignment~(ASA) substitutes the static IoU-based strategy, which enables the student network to be resistant to noisy pseudo-bounding boxes. Then we calibrate the subtask predictions by designing a 3D feature alignment module~(FAM-3D). It allows each classification feature to adaptively query the optimal feature vector for the regression task at arbitrary scales and locations. Lastly, a Gaussian Mixture Model (GMM) dynamically revises the score threshold of pseudo-bboxes, which stabilizes the number of ground truths at an early stage and remedies the unreliable supervision signal during training. ConsistentTeacher provides strong results on a large range of SSOD evaluations. It achieves 40.0 mAP with ResNet-50 backbone given only 10% of annotated MS-COCO data, which surpasses previous baselines using pseudo labels by around 3 mAP. When trained on fully annotated MS-COCO with additional unlabeled data, the performance further increases to 47.7 mAP. Our code is available at \url{https://github.com/Adamdad/ConsistentTeacher}.

PaperPDFConference PDFCode

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

Code

adamdad/consistentteacher officialmentioned in papermentioned 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

Object DetectionSemi-Supervised Object Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Object Detection COCO 1% labeled data Consistent-Teacher mAP 25.5 #5 of 22 Archive leaderboard report
Semi-Supervised Object Detection COCO 10% labeled data Consistent-Teacher detector RetinaNet-Res50 #3 of 27 Archive leaderboard report
Semi-Supervised Object Detection COCO 10% labeled data Consistent-Teacher mAP 40.0 #3 of 27 Archive leaderboard report
Semi-Supervised Object Detection COCO 100% labeled data Consistent-Teacher mAP 48.20 #3 of 13 Archive leaderboard report
Semi-Supervised Object Detection COCO 2% labeled data Consistent-Teacher mAP 30.7 #2 of 19 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.

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