Papers › Rethinking Pseudo Labels for Semi-Supervised Object Detection

Rethinking Pseudo Labels for Semi-Supervised Object Detection

1 Jun 2021arXiv:2106.00168archive 2025-07-28

Hengduo Li, Zuxuan Wu, Abhinav Shrivastava, Larry S. Davis

Recent advances in semi-supervised object detection (SSOD) are largely driven by consistency-based pseudo-labeling methods for image classification tasks, producing pseudo labels as supervisory signals. However, when using pseudo labels, there is a lack of consideration in localization precision and amplified class imbalance, both of which are critical for detection tasks. In this paper, we introduce certainty-aware pseudo labels tailored for object detection, which can effectively estimate the classification and localization quality of derived pseudo labels. This is achieved by converting conventional localization as a classification task followed by refinement. Conditioned on classification and localization quality scores, we dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem. Extensive experiments demonstrate that our method improves state-of-the-art SSOD performance by 1-2% AP on COCO and PASCAL VOC while being orthogonal and complementary to most existing methods. In the limited-annotation regime, our approach improves supervised baselines by up to 10% AP using only 1-10% labeled data from COCO.

PaperPDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

ClassificationImage ClassificationObjectObject DetectionSemi-Supervised Object Detectionimage-classificationobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Object Detection COCO 1% labeled data RPL mAP 19.02 ± 0.25 #18 of 22 Archive leaderboard report
Semi-Supervised Object Detection COCO 10% labeled data RPL mAP 32.23± 0.14 #19 of 27 Archive leaderboard report
Semi-Supervised Object Detection COCO 100% labeled data RPL mAP 43.3 #8 of 13 Archive leaderboard report
Semi-Supervised Object Detection COCO 2% labeled data RPL mAP 23.34± 0.18 #13 of 19 Archive leaderboard report
Semi-Supervised Object Detection COCO 5% labeled data RPL mAP 28.4 ± 0.15 #19 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