This is the official PyTorch implementation of our CVPR 2022 paper:

ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation
Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao
In Conference on Computer Vision and Pattern Recognition (CVPR), 2022

ResNet-50 | ResNet-101 | DeepLabv2-ResNet-101

Pascal JPEGImages | Pascal SegmentationClass | Cityscapes leftImg8bit | Cityscapes gtFine

├── ./pretrained
    ├── resnet50.pth
    ├── resnet101.pth
    └── deeplabv2_resnet101_coco_pretrained.pth
    
├── [Your Pascal Path]
    ├── JPEGImages
    └── SegmentationClass
    
├── [Your Cityscapes Path]
    ├── leftImg8bit
    └── gtFine

export semi_setting='pascal/1_8/split_0'

CUDA_VISIBLE_DEVICES=0,1 python -W ignore main.py \
  --dataset pascal --data-root [Your Pascal Path] \
  --batch-size 16 --backbone resnet50 --model deeplabv3plus \
  --labeled-id-path dataset/splits/$semi_setting/labeled.txt \
  --unlabeled-id-path dataset/splits/$semi_setting/unlabeled.txt \
  --pseudo-mask-path outdir/pseudo_masks/$semi_setting \
  --save-path outdir/models/$semi_setting

This script is for our ST framework. To run ST++, add --plus --reliable-id-path outdir/reliable_ids/$semi_setting.

The DeepLabv2 MS COCO pre-trained model is borrowed and converted from AdvSemiSeg. The image partitions are borrowed from Context-Aware-Consistency and PseudoSeg. Part of the training hyper-parameters and network structures are adapted from PyTorch-Encoding. The strong data augmentations are borrowed from MoCo v2 and PseudoSeg.

• AdvSemiSeg: https://github.com/hfslyc/AdvSemiSeg.
• Context-Aware-Consistency: https://github.com/dvlab-research/Context-Aware-Consistency.
• PseudoSeg: https://github.com/googleinterns/wss.
• PyTorch-Encoding: https://github.com/zhanghang1989/PyTorch-Encoding.
• MoCo: https://github.com/facebookresearch/moco.
• OpenSelfSup: https://github.com/open-mmlab/OpenSelfSup.

Thanks a lot for their great works!

If you find this project useful, please consider citing:

@inproceedings{yang2021st++,
  title={ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentation},
  author={Yang, Lihe and Zhuo, Wei and Qi, Lei and Shi, Yinghuan and Gao, Yang},
  booktitle={CVPR},
  year={2022}
}