Papers › UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation

UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation

20 May 2022CVPR 2022 1arXiv:2205.10334archive 2025-07-28

Jiashuo Fan, Bin Gao, Huan Jin, Lihui Jiang

Deep neural networks (DNNs) have witnessed great successes in semantic segmentation, which requires a large number of labeled data for training. We present a novel learning framework called Uncertainty guided Cross-head Co-training (UCC) for semi-supervised semantic segmentation. Our framework introduces weak and strong augmentations within a shared encoder to achieve co-training, which naturally combines the benefits of consistency and self-training. Every segmentation head interacts with its peers and, the weak augmentation result is used for supervising the strong. The consistency training samples' diversity can be boosted by Dynamic Cross-Set Copy-Paste (DCSCP), which also alleviates the distribution mismatch and class imbalance problems. Moreover, our proposed Uncertainty Guided Re-weight Module (UGRM) enhances the self-training pseudo labels by suppressing the effect of the low-quality pseudo labels from its peer via modeling uncertainty. Extensive experiments on Cityscapes and PASCAL VOC 2012 demonstrate the effectiveness of our UCC. Our approach significantly outperforms other state-of-the-art semi-supervised semantic segmentation methods. It achieves 77.17%, 76.49% mIoU on Cityscapes and PASCAL VOC 2012 datasets respectively under 1/16 protocols, which are +10.1%, +7.91% better than the supervised baseline.

PaperPDFConference PDFCode

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

Code

voldemortX/DST-CBC officialpytorch 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

DiversitySegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Copy-Paste

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