* [Enhancement] Change readme style and prepare for metafiles update. * Update apcnet github repo url. * add code snippet. * split code snippet & official repo. * update md2yml hook. * Update metafiles. * Add converted from attribute. * process conflict. * Put defualt variable value. * update bisenet v2 metafile. * checkout to ubuntu environment. * pop empty attribute & make task attribute list. * update readme style * update readme style * update metafiles Co-authored-by: Junjun2016 <hejunjun@sjtu.edu.cn> |
||
---|---|---|
.. | ||
README.md | ||
isanet.yml | ||
isanet_r50-d8_512x512_20k_voc12aug.py | ||
isanet_r50-d8_512x512_40k_voc12aug.py | ||
isanet_r50-d8_512x512_80k_ade20k.py | ||
isanet_r50-d8_512x512_160k_ade20k.py | ||
isanet_r50-d8_512x1024_40k_cityscapes.py | ||
isanet_r50-d8_512x1024_80k_cityscapes.py | ||
isanet_r50-d8_769x769_40k_cityscapes.py | ||
isanet_r50-d8_769x769_80k_cityscapes.py | ||
isanet_r101-d8_512x512_20k_voc12aug.py | ||
isanet_r101-d8_512x512_40k_voc12aug.py | ||
isanet_r101-d8_512x512_80k_ade20k.py | ||
isanet_r101-d8_512x512_160k_ade20k.py | ||
isanet_r101-d8_512x1024_40k_cityscapes.py | ||
isanet_r101-d8_512x1024_80k_cityscapes.py | ||
isanet_r101-d8_769x769_40k_cityscapes.py | ||
isanet_r101-d8_769x769_80k_cityscapes.py |
README.md
Interlaced Sparse Self-Attention for Semantic Segmentation
Introduction
ISANet (ArXiv'2019/IJCV'2021)
@article{huang2019isa,
title={Interlaced Sparse Self-Attention for Semantic Segmentation},
author={Huang, Lang and Yuan, Yuhui and Guo, Jianyuan and Zhang, Chao and Chen, Xilin and Wang, Jingdong},
journal={arXiv preprint arXiv:1907.12273},
year={2019}
}
The technical report above is also presented at:
@article{yuan2021ocnet,
title={OCNet: Object Context for Semantic Segmentation},
author={Yuan, Yuhui and Huang, Lang and Guo, Jianyuan and Zhang, Chao and Chen, Xilin and Wang, Jingdong},
journal={International Journal of Computer Vision},
pages={1--24},
year={2021},
publisher={Springer}
}
Results and models
Cityscapes
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
ISANet | R-50-D8 | 512x1024 | 40000 | 5.869 | 2.91 | 78.49 | 79.44 | config | model | log |
ISANet | R-50-D8 | 512x1024 | 80000 | 5.869 | 2.91 | 78.68 | 80.25 | config | model | log |
ISANet | R-50-D8 | 769x769 | 40000 | 6.759 | 1.54 | 78.70 | 80.28 | config | model | log |
ISANet | R-50-D8 | 769x769 | 80000 | 6.759 | 1.54 | 79.29 | 80.53 | config | model | log |
ISANet | R-101-D8 | 512x1024 | 40000 | 9.425 | 2.35 | 79.58 | 81.05 | config | model | log |
ISANet | R-101-D8 | 512x1024 | 80000 | 9.425 | 2.35 | 80.32 | 81.58 | config | model | log |
ISANet | R-101-D8 | 769x769 | 40000 | 10.815 | 0.92 | 79.68 | 80.95 | config | model | log |
ISANet | R-101-D8 | 769x769 | 80000 | 10.815 | 0.92 | 80.61 | 81.59 | config | model | log |
ADE20K
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
ISANet | R-50-D8 | 512x512 | 80000 | 9.0 | 22.55 | 41.12 | 42.35 | config | model | log |
ISANet | R-50-D8 | 512x512 | 160000 | 9.0 | 22.55 | 42.59 | 43.07 | config | model | log |
ISANet | R-101-D8 | 512x512 | 80000 | 12.562 | 10.56 | 43.51 | 44.38 | config | model | log |
ISANet | R-101-D8 | 512x512 | 160000 | 12.562 | 10.56 | 43.80 | 45.4 | config | model | log |
Pascal VOC 2012 + Aug
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
ISANet | R-50-D8 | 512x512 | 20000 | 5.9 | 23.08 | 76.78 | 77.79 | config | model | log |
ISANet | R-50-D8 | 512x512 | 40000 | 5.9 | 23.08 | 76.20 | 77.22 | config | model | log |
ISANet | R-101-D8 | 512x512 | 20000 | 9.465 | 7.42 | 78.46 | 79.16 | config | model | log |
ISANet | R-101-D8 | 512x512 | 40000 | 9.465 | 7.42 | 78.12 | 79.04 | config | model | log |