This repository contains the official implementation of the following paper:

CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation
Boyuan Sun, Yuqi Yang, Weifeng Yuan, Le Zhang, Ming-Ming Cheng, Qibin Hou

CorrMatch provides a solution for mining more high-quality regions from the unlabeled images to leverage the unlabeled data more efficiently for consistency regularization.

We first introduce an adaptive threshold updating strategy with a relaxed initialization to expand the high-quality regions. Then we propose to propagate high-confidence predictions with correlation maps.

For technical details, please refer to our full paper on arXiv.

git clone git@github.com:BBBBchan/CorrMatch.git
cd CorrMatch
conda create -n corrmatch python=3.8
conda activate corrmatch
conda install pytorch==1.13.1 torchvision==0.14.1 torchaudio==0.13.1 pytorch-cuda=11.7 -c pytorch -c nvidia
pip install opencv-python tqdm einops pyyaml

ResNet-101

mkdir pretrained

Please put the pretrained model under pretrained dictionary.

• Pascal VOC 2012: JPEGImages | SegmentationClass
• Cityscapes: leftImg8bit | gtFine

Please modify the dataset path in configuration files.The groundtruth mask ids have already been pre-processed. You may use them directly.

Your dataset path may look like:

├── [Your Pascal Path]
    ├── JPEGImages
    └── SegmentationClass
    
├── [Your Cityscapes Path]
    ├── leftImg8bit
    └── gtFine

sh tools/train.sh <num_gpu> <port>

To run on different labeled data partitions or different datasets, please modify:

config, labeled_id_path, unlabeled_id_path, and save_path in train.sh.

sh tools/val.sh <num_gpu> <port>

To evaluate your checkpoint, please modify checkpoint_path in val.sh.

Labeled images are sampled from the original high-quality training set. Results are obtained by DeepLabv3+ based on ResNet-101 with training size 321(513).

Results are obtained by DeepLabv3+ based on ResNet-101.

If you find our repo useful for your research, please consider citing our paper:

@article{sun2023corrmatch,
  title={CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentation},
  author={Sun, Boyuan and Yang, Yuqi and Yuan, Weifeng and Zhang, Le and Cheng, Ming-Ming and Hou, Qibin},
  journal={arXiv preprint arXiv:2306.04300},
  year={2023}
}

This code is licensed under the Creative Commons Attribution-NonCommercial 4.0 International for non-commercial use only. Please note that any commercial use of this code requires formal permission prior to use.

For technical questions, please contact sbysbysby123[AT]gmail.com.

For commercial licensing, please contact cmm[AT]nankai.edu.cn or andrewhoux@gmail.com.

We thank UniMatch, CPS, CutMix-Seg, DeepLabv3Plus, U²PL and other excellent works (see this project) for their amazing projects!