Papers › PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
PseCo: Pseudo Labeling and Consistency Training for Semi-Supervised Object Detection
Gang Li, Xiang Li, Yujie Wang, Yichao Wu, Ding Liang, Shanshan Zhang
In this paper, we delve into two key techniques in Semi-Supervised Object Detection (SSOD), namely pseudo labeling and consistency training. We observe that these two techniques currently neglect some important properties of object detection, hindering efficient learning on unlabeled data. Specifically, for pseudo labeling, existing works only focus on the classification score yet fail to guarantee the localization precision of pseudo boxes; For consistency training, the widely adopted random-resize training only considers the label-level consistency but misses the feature-level one, which also plays an important role in ensuring the scale invariance. To address the problems incurred by noisy pseudo boxes, we design Noisy Pseudo box Learning (NPL) that includes Prediction-guided Label Assignment (PLA) and Positive-proposal Consistency Voting (PCV). PLA relies on model predictions to assign labels and makes it robust to even coarse pseudo boxes; while PCV leverages the regression consistency of positive proposals to reflect the localization quality of pseudo boxes. Furthermore, in consistency training, we propose Multi-view Scale-invariant Learning (MSL) that includes mechanisms of both label- and feature-level consistency, where feature consistency is achieved by aligning shifted feature pyramids between two images with identical content but varied scales. On COCO benchmark, our method, termed PSEudo labeling and COnsistency training (PseCo), outperforms the SOTA (Soft Teacher) by 2.0, 1.8, 2.0 points under 1%, 5%, and 10% labelling ratios, respectively. It also significantly improves the learning efficiency for SSOD, e.g., PseCo halves the training time of the SOTA approach but achieves even better performance. Code is available at https://github.com/ligang-cs/PseCo.
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 | PseCo | mAP | 22.43 | #12 of 22 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 10% labeled data | PseCo | detector | FasterRCNN-Res50 | #10 of 27 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 10% labeled data | PseCo | mAP | 36.06 | #10 of 27 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 100% labeled data | PseCo | mAP | 46.1 | #5 of 13 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 2% labeled data | PseCo | mAP | 27.77 | #9 of 19 | Archive leaderboard | report |
| Semi-Supervised Object Detection | COCO 5% labeled data | PseCo | mAP | 32.5 | #8 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