Papers › Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression...

Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertainty

6 Dec 2022arXiv:2212.02747archive 2025-07-28

Honggyu Choi, Zhixiang Chen, Xuepeng Shi, Tae-Kyun Kim

Semi-supervised object detection (SSOD) aims to boost detection performance by leveraging extra unlabeled data. The teacher-student framework has been shown to be promising for SSOD, in which a teacher network generates pseudo-labels for unlabeled data to assist the training of a student network. Since the pseudo-labels are noisy, filtering the pseudo-labels is crucial to exploit the potential of such framework. Unlike existing suboptimal methods, we propose a two-step pseudo-label filtering for the classification and regression heads in a teacher-student framework. For the classification head, OCL (Object-wise Contrastive Learning) regularizes the object representation learning that utilizes unlabeled data to improve pseudo-label filtering by enhancing the discriminativeness of the classification score. This is designed to pull together objects in the same class and push away objects from different classes. For the regression head, we further propose RUPL (Regression-Uncertainty-guided Pseudo-Labeling) to learn the aleatoric uncertainty of object localization for label filtering. By jointly filtering the pseudo-labels for the classification and regression heads, the student network receives better guidance from the teacher network for object detection task. Experimental results on Pascal VOC and MS-COCO datasets demonstrate the superiority of our proposed method with competitive performance compared to existing methods.

Paper PDF

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

Classification Contrastive Learning Object Object Detection Object Localization Pseudo Label Pseudo Label Filtering Representation Learning Semi-Supervised Object Detection object-detection regression

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	SSOD with OCL and RUPL	mAP	21.63	#14 of 22	Archive leaderboard	report
Semi-Supervised Object Detection	COCO 10% labeled data	SSOD with OCL and RUPL	mAP	33.53	#18 of 27	Archive leaderboard	report
Semi-Supervised Object Detection	COCO 5% labeled data	SSOD with OCL and RUPL	mAP	30.66	#15 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