Papers › Mixed Pseudo Labels for Semi-Supervised Object Detection

Mixed Pseudo Labels for Semi-Supervised Object Detection

12 Dec 2023arXiv:2312.07006archive 2025-07-28

Zeming Chen, Wenwei Zhang, Xinjiang Wang, Kai Chen, Zhi Wang

While the pseudo-label method has demonstrated considerable success in semi-supervised object detection tasks, this paper uncovers notable limitations within this approach. Specifically, the pseudo-label method tends to amplify the inherent strengths of the detector while accentuating its weaknesses, which is manifested in the missed detection of pseudo-labels, particularly for small and tail category objects. To overcome these challenges, this paper proposes Mixed Pseudo Labels (MixPL), consisting of Mixup and Mosaic for pseudo-labeled data, to mitigate the negative impact of missed detections and balance the model's learning across different object scales. Additionally, the model's detection performance on tail categories is improved by resampling labeled data with relevant instances. Notably, MixPL consistently improves the performance of various detectors and obtains new state-of-the-art results with Faster R-CNN, FCOS, and DINO on COCO-Standard and COCO-Full benchmarks. Furthermore, MixPL also exhibits good scalability on large models, improving DINO Swin-L by 2.5% mAP and achieving nontrivial new records (60.2% mAP) on the COCO val2017 benchmark without extra annotations.

Paper PDF Code

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

Code

czm369/mixpl officialmentioned in paperpytorch 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 Object Detection Pseudo Label Semi-Supervised Object Detection object-detection

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	MixPL	mAP	31.7	#1 of 22	Archive leaderboard	report
Semi-Supervised Object Detection	COCO 10% labeled data	MixPL	detector	DINO-Res50	#1 of 27	Archive leaderboard	report
Semi-Supervised Object Detection	COCO 10% labeled data	MixPL	mAP	44.6	#1 of 27	Archive leaderboard	report
Semi-Supervised Object Detection	COCO 100% labeled data	MixPL	mAP	55.2	#1 of 13	Archive leaderboard	report
Semi-Supervised Object Detection	COCO 2% labeled data	MixPL	mAP	34.7	#1 of 19	Archive leaderboard	report
Semi-Supervised Object Detection	COCO 5% labeled data	MixPL	mAP	40.1	#2 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

1x1 Convolution Attention Convolution DINO Dense Connections FCOS FPN Faster R-CNN Layer Normalization Linear Layer Mixup Multi-Head Attention Non Maximum Suppression RPN Residual Connection RoIPool Softmax Vision Transformer

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