Awesome

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

What's New

• 2024-08-05: Support SAMV2, refer to inference-with-samv2 for more details.
• 2023-12-20: Support EdgeSAM and SAMHQ, refer to inference-with-edgesam and inference-with-samhq for more details.
• 2023-10-25: Support ConvNeXtV2, refer to Results and Models for ConvNeXtV2 for more details.
• 2023-10-23: Support MobileViT and MobileViTV2, refer to Results and Models for MobileViT for more details.
• 2023-10-18: Support Mask2Former, refer to Results and Models for Mask2Former for more details.
• 2023-10-17: We release the source codes of IDRNet: Intervention-Driven Relation Network for Semantic Segmentation, which was accepted by NeurIPS 2023, refer to Results and Models for IDRNet for more details.
• 2023-10-15: Support MobileSAM, refer to inference-with-mobilesam for more details.
• 2023-09-27: Support SAM, refer to inference-with-sam for more details.

Introduction

SSSegmentation is an open source 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

• High Performance

  The performance of re-implemented segmentation algorithms is better than or comparable to other codebases.

• Modular Design and Unified Benchmark

  Various segmentation methods are unified into several specific modules. Benefiting from this design, SSSegmentation can integrate a great deal of popular and contemporary semantic segmentation frameworks and then, train and test them on unified benchmarks.

• Fewer Dependencies

  SSSegmenation tries its best to avoid introducing more dependencies when reproducing novel semantic segmentation approaches.

Benchmark and Model Zoo

Supported Backbones

Supported Segmentors

Supported Datasets

Citation

If you use SSSegmentation in your research, please consider citing this project,

@article{jin2023sssegmenation,
    title={SSSegmenation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch},
    author={Jin, Zhenchao},
    journal={arXiv preprint arXiv:2305.17091},
    year={2023}
}

@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}
}

@article{jin2022mcibi++,
    title={MCIBI++: Soft Mining Contextual Information Beyond Image for Semantic Segmentation},
    author={Jin, Zhenchao and Yu, Dongdong and Yuan, Zehuan and Yu, Lequan},
    journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
    year={2022},
    publisher={IEEE}
}

@inproceedings{jin2023idrnet,
    title={IDRNet: Intervention-Driven Relation Network for Semantic Segmentation},
    author={Jin, Zhenchao and Hu, Xiaowei and Zhu, Lingting and Song, Luchuan and Yuan, Li and Yu, Lequan},
    booktitle={Thirty-Seventh Conference on Neural Information Processing Systems},
    year={2023}
}

References

We are very grateful to the following projects for their help in building SSSegmentation,

• MMSegmentation
• segment-anything
• MobileSAM
• Mask2Former
• Swin-Transformer
• HRNet-Semantic-Segmentation
• apex
• MMCV
• VSPW_code
• MMPreTrain
• PyTorch Image Models
• EdgeSAM
• sam-hq
• segment-anything-2