Papers › Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
Chang Liu, Weiming Zhang, Xiangru Lin, Wei zhang, Xiao Tan, Junyu Han, Xiaomao Li, Errui Ding, Jingdong Wang
With basic Semi-Supervised Object Detection (SSOD) techniques, one-stage detectors generally obtain limited promotions compared with two-stage clusters. We experimentally find that the root lies in two kinds of ambiguities: (1) Selection ambiguity that selected pseudo labels are less accurate, since classification scores cannot properly represent the localization quality. (2) Assignment ambiguity that samples are matched with improper labels in pseudo-label assignment, as the strategy is misguided by missed objects and inaccurate pseudo boxes. To tackle these problems, we propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors. Specifically, to alleviate the selection ambiguity, Joint-Confidence Estimation (JCE) is proposed to jointly quantifies the classification and localization quality of pseudo labels. As for the assignment ambiguity, Task-Separation Assignment (TSA) is introduced to assign labels based on pixel-level predictions rather than unreliable pseudo boxes. It employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity. Comprehensive experiments demonstrate that ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC. Codes can be found at https://github.com/PaddlePaddle/PaddleDetection.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Semi-Supervised Object Detection | COCO 1% labeled data | ARSL | mAP | 25.36 | #6 of 22 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 10% labeled data | ARSL | detector | FCOS-Res50 | #4 of 27 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 10% labeled data | ARSL | mAP | 38.5 | #4 of 27 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 10% labeled data | Semi-DETR | detector | FCOS-Res50 | #27 of 27 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 2% labeled data | ARSL | mAP | 29.08 | #4 of 19 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 5% labeled data | ARSL | mAP | 34.45 | #3 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.
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