TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/CorrMatch: Label Propagation via Correlation Matching for ...

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

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

2023-06-07CVPR 2024 1Semi-Supervised Semantic SegmentationSegmentationSemantic Segmentation
PaperPDFCode(official)

Abstract

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.

Results

TaskDatasetMetricValueModel
Semantic SegmentationPascal VOC 2012 6.25% labeledValidation mIoU81.3CorrMatch (Deeplabv3+ with ResNet-101)
Semantic SegmentationPASCAL VOC 2012 92 labeledValidation mIoU76.4CorrMatch (Deeplabv3+ with ResNet-101)
Semantic SegmentationPASCAL VOC 2012 732 labeledValidation mIoU80.6CorrMatch (Deeplabv3+ with ResNet-101)
Semantic SegmentationPASCAL VOC 2012 1464 labelsValidation mIoU81.8CorrMatch (Deeplabv3+ with ResNet-101)
Semantic SegmentationPASCAL VOC 2012 25% labeledValidation mIoU80.9CorrMatch (Deeplabv3+ with ResNet-101)
Semantic SegmentationPASCAL VOC 2012 366 labeledValidation mIoU79.4CorrMatch (Deeplabv3+ with ResNet-101)
Semantic SegmentationCityscapes 6.25% labeledValidation mIoU77.3CorrMatch (Deeplabv3+ with ResNet-101)
Semantic SegmentationPASCAL VOC 2012 183 labeledValidation mIoU78.5CorrMatch (Deeplabv3+ with ResNet-101)
10-shot image generationPascal VOC 2012 6.25% labeledValidation mIoU81.3CorrMatch (Deeplabv3+ with ResNet-101)
10-shot image generationPASCAL VOC 2012 92 labeledValidation mIoU76.4CorrMatch (Deeplabv3+ with ResNet-101)
10-shot image generationPASCAL VOC 2012 732 labeledValidation mIoU80.6CorrMatch (Deeplabv3+ with ResNet-101)
10-shot image generationPASCAL VOC 2012 1464 labelsValidation mIoU81.8CorrMatch (Deeplabv3+ with ResNet-101)
10-shot image generationPASCAL VOC 2012 25% labeledValidation mIoU80.9CorrMatch (Deeplabv3+ with ResNet-101)
10-shot image generationPASCAL VOC 2012 366 labeledValidation mIoU79.4CorrMatch (Deeplabv3+ with ResNet-101)
10-shot image generationCityscapes 6.25% labeledValidation mIoU77.3CorrMatch (Deeplabv3+ with ResNet-101)
10-shot image generationPASCAL VOC 2012 183 labeledValidation mIoU78.5CorrMatch (Deeplabv3+ with ResNet-101)

Related Papers

SeC: Advancing Complex Video Object Segmentation via Progressive Concept Construction2025-07-21Deep Learning-Based Fetal Lung Segmentation from Diffusion-weighted MRI Images and Lung Maturity Evaluation for Fetal Growth Restriction2025-07-17DiffOSeg: Omni Medical Image Segmentation via Multi-Expert Collaboration Diffusion Model2025-07-17From Variability To Accuracy: Conditional Bernoulli Diffusion Models with Consensus-Driven Correction for Thin Structure Segmentation2025-07-17Unleashing Vision Foundation Models for Coronary Artery Segmentation: Parallel ViT-CNN Encoding and Variational Fusion2025-07-17SCORE: Scene Context Matters in Open-Vocabulary Remote Sensing Instance Segmentation2025-07-17Unified Medical Image Segmentation with State Space Modeling Snake2025-07-17A Privacy-Preserving Semantic-Segmentation Method Using Domain-Adaptation Technique2025-07-17