SSSegmentation: An Open Source Supervised Semantic Segmentation Toolbox Based on PyTorch
Project description
Documents: https://sssegmentation.readthedocs.io/en/latest/
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
Backbone | Model Zoo | Paper Link | Code Snippet |
---|---|---|---|
UNet | Click | MICCAI 2015 | Click |
BEiT | Click | ICLR 2022 | Click |
Twins | Click | NeurIPS 2021 | Click |
CGNet | Click | TIP 2020 | Click |
HRNet | Click | CVPR 2019 | Click |
ERFNet | Click | T-ITS 2017 | Click |
ResNet | Click | CVPR 2016 | Click |
ResNeSt | Click | ArXiv 2020 | Click |
ConvNeXt | Click | CVPR 2022 | Click |
FastSCNN | Click | ArXiv 2019 | Click |
BiSeNetV1 | Click | ECCV 2018 | Click |
BiSeNetV2 | Click | IJCV 2021 | Click |
MobileNetV2 | Click | CVPR 2018 | Click |
MobileNetV3 | Click | ICCV 2019 | Click |
SwinTransformer | Click | ICCV 2021 | Click |
VisionTransformer | Click | IClR 2021 | Click |
Supported Segmentors
Segmentor | Model Zoo | Paper Link | Code Snippet |
---|---|---|---|
FCN | Click | TPAMI 2017 | Click |
CE2P | Click | AAAI 2019 | Click |
SETR | Click | CVPR 2021 | Click |
ISNet | Click | ICCV 2021 | Click |
ICNet | Click | ECCV 2018 | Click |
CCNet | Click | ICCV 2019 | Click |
DANet | Click | CVPR 2019 | Click |
DMNet | Click | ICCV 2019 | Click |
GCNet | Click | TPAMI 2020 | Click |
ISANet | Click | IJCV 2021 | Click |
EncNet | Click | CVPR 2018 | Click |
OCRNet | Click | ECCV 2020 | Click |
DNLNet | Click | ECCV 2020 | Click |
ANNNet | Click | ICCV 2019 | Click |
EMANet | Click | ICCV 2019 | Click |
PSPNet | Click | CVPR 2017 | Click |
PSANet | Click | ECCV 2018 | Click |
APCNet | Click | CVPR 2019 | Click |
FastFCN | Click | ArXiv 2019 | Click |
UPerNet | Click | ECCV 2018 | Click |
PointRend | Click | CVPR 2020 | Click |
Deeplabv3 | Click | ArXiv 2017 | Click |
Segformer | Click | NeurIPS 2021 | Click |
MaskFormer | Click | NeurIPS 2021 | Click |
SemanticFPN | Click | CVPR 2019 | Click |
NonLocalNet | Click | CVPR 2018 | Click |
Deeplabv3Plus | Click | ECCV 2018 | Click |
MemoryNet-MCIBI | Click | ICCV 2021 | Click |
MemoryNet-MCIBI++ | Click | TPAMI 2022 | Click |
Mixed Precision (FP16) Training | Click | ArXiv 2017 | Click |
Supported Datasets
Dataset | Project Link | Paper Link | Code Snippet |
---|---|---|---|
LIP | Click | CVPR 2017 | Click |
ATR | Click | ICCV 2015 | Click |
HRF | Click | Int J Biomed Sci 2013 | Click |
CIHP | Click | ECCV 2018 | Click |
VSPW | Click | CVPR 2021 | Click |
DRIVE | Click | TMI 2004 | Click |
STARE | Click | TMI 2000 | Click |
ADE20k | Click | CVPR 2017 | Click |
MS COCO | Click | ECCV 2014 | Click |
MHPv1&v2 | Click | ArXiv 2017 | Click |
CHASE DB1 | Click | TBME 2012 | Click |
CityScapes | Click | CVPR 2016 | Click |
Supervisely | Click | Website Release 2022 | Click |
PASCAL VOC | Click | IJCV 2010 | Click |
SBUShadow | Click | ECCV 2016 | Click |
Dark Zurich | Click | ICCV 2019 | Click |
COCOStuff10k | Click | CVPR 2018 | Click |
COCOStuff164k | Click | CVPR 2018 | Click |
Pascal Context | Click | CVPR 2014 | Click |
Nighttime Driving | Click | ITSC 2018 | Click |
Citation
If you use this framework in your research, please cite 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}
}
References
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file SSSegmentation-1.3.0.tar.gz
.
File metadata
- Download URL: SSSegmentation-1.3.0.tar.gz
- Upload date:
- Size: 133.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.12.0 pkginfo/1.7.0 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.7.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 707ccf7f9742a28dbe298e217efd3783143974c57a7f266df3d0acff713faee1 |
|
MD5 | c9d873f3046c36e35614185e75df90af |
|
BLAKE2b-256 | 74cc1041feb316591fa1e0a14f36ded642b18fbb508f0d11d23a0f94cb382eda |
File details
Details for the file SSSegmentation-1.3.0-py3-none-any.whl
.
File metadata
- Download URL: SSSegmentation-1.3.0-py3-none-any.whl
- Upload date:
- Size: 254.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/4.12.0 pkginfo/1.7.0 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.60.0 CPython/3.7.8
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | d8e9f08a33da31ff941c6b57b6852ce46c6b5fdc44aa5b556ec9c8d7adb992a6 |
|
MD5 | c2e1d14a35a2b1e8e6f5adac065a1909 |
|
BLAKE2b-256 | 4824897fa8aedcfa713c760374a7f6742698dd95ea0918c3dd0b3165a415736f |