SSSegmentation 1.0.0

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

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

Introduction

SSSegmentation is an open source strongly supervised semantic segmentation toolbox based on PyTorch. You can star this repository to keep track of the project if it's helpful for you, thank you for your support.

Major Features

• Unified Benchmark

  We provide a unified benchmark toolbox for various semantic segmentation methods.

• Modular Design

  We decompose the semantic segmentation framework into different components and one can easily construct a customized semantic segmentation framework by combining different modules.

• Support of Multiple Methods Out of Box

  The toolbox directly supports popular and contemporary semantic segmentation frameworks, e.g. ISNet, DeepLabV3, PSPNet, MCIBI, etc.

• High Performance

  The segmentation performance is better than or comparable to other codebases.

Benchmark and Model Zoo

Supported Backbones

• UNet
• Twins
• CGNet
• HRNet
• ERFNet
• ResNet
• ResNeSt
• FastSCNN
• BiSeNetV1
• BiSeNetV2
• MobileNetV2
• MobileNetV3
• SwinTransformer
• VisionTransformer

Supported Segmentors

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

Supported Datasets

• LIP
• ATR
• HRF
• CIHP
• VSPW
• DRIVE
• STARE
• ADE20k
• MS COCO
• MHPv1&v2
• CHASE DB1
• CityScapes
• Supervisely
• SBUShadow
• PASCAL VOC
• COCOStuff10k
• COCOStuff164k
• Pascal Context

Citation

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

@misc{ssseg2020,
    author = {Zhenchao Jin},
    title = {SSSegmentation: An Open Source Strongly Supervised Semantic Segmentation Toolbox Based on PyTorch},
    year = {2020},
    publisher = {GitHub},
    journal = {GitHub repository},
    howpublished = {\url{https://github.com/SegmentationBLWX/sssegmentation}},
}

@inproceedings{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},
    booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
    pages={7189--7198},
    year={2021}
}

@inproceedings{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},
    booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
    pages={7231--7241},
    year={2021}
}

References

• MMCV
• MMSegmentation