liuzhidemaomao / sssegmentation

sssegmentation is a general framework for our research on strongly supervised semantic segmentation.

Introduction

sssegmentation is a general framework for our research on strongly supervised semantic segmentation.

Documents

In English

https://sssegmentation.readthedocs.io/en/latest/

Supported

Supported Backbones

• UNet
• CGNet
• HRNet
• ResNet
• ResNeSt
• MobileNetV2
• MobileNetV3
• SwinTransformer
• VisionTransformer

Supported Models

• FCN
• CE2P
• SETR
• ISNet
• CCNet
• DANet
• GCNet
• DMNet
• ISANet
• EncNet
• OCRNet
• DNLNet
• ANNNet
• EMANet
• PSPNet
• PSANet
• APCNet
• UPerNet
• PointRend
• Deeplabv3
• Segformer
• SemanticFPN
• NonLocalNet
• Deeplabv3Plus
• MemoryNet-MCIBI
• Mixed Precision (FP16) Training

Supported Datasets

• LIP
• ATR
• HRF
• CIHP
• DRIVE
• STARE
• ADE20k
• MS COCO
• MHPv1&v2
• CHASE DB1
• CityScapes
• Supervisely
• SBUShadow
• PASCAL VOC
• COCOStuff10k
• Pascal Context

Citation

If you use this framework in your research, please cite this project:

@misc{ssseg2020,
    author = {Zhenchao Jin},
    title = {SSSegmentation: A general framework for strongly supervised semantic segmentation},
    year = {2020},
    publisher = {GitHub},
    journal = {GitHub repository},
    howpublished = {\url{https://github.com/SegmentationBLWX/sssegmentation}},
}

@article{jin2021isnet,
  title={ISNet: Integrate Image-Level and Semantic-Level Context for Semantic Segmentation},
  author={Jin, Zhenchao and Liu, Bin and Chu, Qi and Yu, Nenghai},
  journal={arXiv preprint arXiv:2108.12382},
  year={2021}
}

@article{jin2021mining,
  title={Mining Contextual Information Beyond Image for Semantic Segmentation},
  author={Jin, Zhenchao and Gong, Tao and Yu, Dongdong and Chu, Qi and Wang, Jian and Wang, Changhu and Shao, Jie},
  journal={arXiv preprint arXiv:2108.11819},
  year={2021}
}

References

[1]. https://github.com/open-mmlab/mmcv
[2]. https://github.com/open-mmlab/mmsegmentation