README.md

August 10, 2025 ยท View on GitHub


Docs PyPI - Python Version PyPI License PyPI - Downloads PyPI - Downloads Release - Downloads Issue Resolution Open Issues GitHub Last Commit (Main)

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

What's New

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

BackboneModel ZooPaper LinkCode Snippet
ConvNeXtV2ClickCVPR 2023Click
MobileViTV2ClickArXiv 2022Click
ConvNeXtClickCVPR 2022Click
MAEClickCVPR 2022Click
MobileViTClickICLR 2022Click
BEiTClickICLR 2022Click
TwinsClickNeurIPS 2021Click
SwinTransformerClickICCV 2021Click
VisionTransformerClickIClR 2021Click
BiSeNetV2ClickIJCV 2021Click
ResNeStClickArXiv 2020Click
CGNetClickTIP 2020Click
HRNetClickCVPR 2019Click
MobileNetV3ClickICCV 2019Click
FastSCNNClickArXiv 2019Click
BiSeNetV1ClickECCV 2018Click
MobileNetV2ClickCVPR 2018Click
ERFNetClickT-ITS 2017Click
ResNetClickCVPR 2016Click
UNetClickMICCAI 2015Click

Supported Segmentors

SegmentorModel ZooPaper LinkCode Snippet
SAMV2ClickArXiv 2024Click
EdgeSAMClickArXiv 2023Click
IDRNetClickNeurIPS 2023Click
MobileSAMClickArXiv 2023Click
SAMHQClickNeurIPS 2023Click
SAMClickArXiv 2023Click
MCIBI++ClickTPAMI 2022Click
Mask2FormerClickCVPR 2022Click
ISNetClickICCV 2021Click
MCIBIClickICCV 2021Click
MaskFormerClickNeurIPS 2021Click
SegformerClickNeurIPS 2021Click
SETRClickCVPR 2021Click
ISANetClickIJCV 2021Click
DNLNetClickECCV 2020Click
PointRendClickCVPR 2020Click
OCRNetClickECCV 2020Click
GCNetClickTPAMI 2020Click
APCNetClickCVPR 2019Click
DMNetClickICCV 2019Click
ANNNetClickICCV 2019Click
EMANetClickICCV 2019Click
FastFCNClickArXiv 2019Click
SemanticFPNClickCVPR 2019Click
CCNetClickICCV 2019Click
CE2PClickAAAI 2019Click
DANetClickCVPR 2019Click
PSANetClickECCV 2018Click
UPerNetClickECCV 2018Click
EncNetClickCVPR 2018Click
Deeplabv3PlusClickECCV 2018Click
NonLocalNetClickCVPR 2018Click
ICNetClickECCV 2018Click
Mixed Precision (FP16) TrainingClickArXiv 2017Click
Deeplabv3ClickArXiv 2017Click
PSPNetClickCVPR 2017Click
FCNClickTPAMI 2017Click

Supported Datasets

DatasetProject LinkPaper LinkCode SnippetDownload Script
VSPWClickCVPR 2021Click
CMD bash scripts/prepare_datasets.sh vspw
SuperviselyClickWebsite Release 2020Click
CMD bash scripts/prepare_datasets.sh supervisely
Dark ZurichClickICCV 2019Click
CMD bash scripts/prepare_datasets.sh darkzurich
Nighttime DrivingClickITSC 2018Click
CMD bash scripts/prepare_datasets.sh nighttimedriving
CIHPClickECCV 2018Click
CMD bash scripts/prepare_datasets.sh cihp
COCOStuff10kClickCVPR 2018Click
CMD bash scripts/prepare_datasets.sh cocostuff10k
COCOStuff164kClickCVPR 2018Click
CMD bash scripts/prepare_datasets.sh coco
MHPv1&v2ClickArXiv 2017Click
CMD bash scripts/prepare_datasets.sh mhpv1 & bash scripts/prepare_datasets.sh mhpv2
LIPClickCVPR 2017Click
CMD bash scripts/prepare_datasets.sh lip
ADE20kClickCVPR 2017Click
CMD bash scripts/prepare_datasets.sh ade20k
SBUShadowClickECCV 2016Click
CMD bash scripts/prepare_datasets.sh sbushadow
CityScapesClickCVPR 2016Click
CMD bash scripts/prepare_datasets.sh cityscapes
ATRClickICCV 2015Click
CMD bash scripts/prepare_datasets.sh atr
Pascal ContextClickCVPR 2014Click
CMD bash scripts/prepare_datasets.sh pascalcontext
MS COCOClickECCV 2014Click
CMD bash scripts/prepare_datasets.sh coco
HRFClickInt J Biomed Sci 2013Click
CMD bash scripts/prepare_datasets.sh hrf
CHASE DB1ClickTBME 2012Click
CMD bash scripts/prepare_datasets.sh chase_db1
PASCAL VOCClickIJCV 2010Click
CMD bash scripts/prepare_datasets.sh pascalvoc
DRIVEClickTMI 2004Click
CMD bash scripts/prepare_datasets.sh drive
STAREClickTMI 2000Click
CMD bash scripts/prepare_datasets.sh stare

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,