Papers › CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation

CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation

7 Jun 2023CVPR 2024 1arXiv:2306.04300archive 2025-07-28

Boyuan Sun, YuQi Yang, Le Zhang, Ming-Ming Cheng, Qibin Hou

This paper presents a simple but performant semi-supervised semantic segmentation approach, called CorrMatch. Previous approaches mostly employ complicated training strategies to leverage unlabeled data but overlook the role of correlation maps in modeling the relationships between pairs of locations. We observe that the correlation maps not only enable clustering pixels of the same category easily but also contain good shape information, which previous works have omitted. Motivated by these, we aim to improve the use efficiency of unlabeled data by designing two novel label propagation strategies. First, we propose to conduct pixel propagation by modeling the pairwise similarities of pixels to spread the high-confidence pixels and dig out more. Then, we perform region propagation to enhance the pseudo labels with accurate class-agnostic masks extracted from the correlation maps. CorrMatch achieves great performance on popular segmentation benchmarks. Taking the DeepLabV3+ with ResNet-101 backbone as our segmentation model, we receive a 76%+ mIoU score on the Pascal VOC 2012 dataset with only 92 annotated images. Code is available at https://github.com/BBBBchan/CorrMatch.

PaperPDFConference PDFCode

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

Code

bbbbchan/corrmatch officialmentioned in papermentioned on GitHubpytorch 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

SegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semi-Supervised Semantic Segmentation Cityscapes 12.5% labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 78.5% #4 of 33 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 25% labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 79.4% #7 of 30 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 50% labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 80.4% #5 of 23 Archive leaderboard report
Semi-Supervised Semantic Segmentation Cityscapes 6.25% labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 77.3 #4 of 18 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 1464 labels CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 81.8 #6 of 17 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 183 labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 78.5 #8 of 16 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 25% labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 80.9 #5 of 27 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 366 labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 79.4 #8 of 15 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 732 labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 80.6 #7 of 16 Archive leaderboard report
Semi-Supervised Semantic Segmentation PASCAL VOC 2012 92 labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 76.4 #8 of 17 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 12.5% labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 81.9% #6 of 38 Archive leaderboard report
Semi-Supervised Semantic Segmentation Pascal VOC 2012 6.25% labeled CorrMatch (Deeplabv3+ with ResNet-101) Validation mIoU 81.3 #5 of 19 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