| # GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond | |
| ## Introduction | |
| [ALGORITHM] | |
| ```latex | |
| @inproceedings{cao2019gcnet, | |
| title={Gcnet: Non-local networks meet squeeze-excitation networks and beyond}, | |
| author={Cao, Yue and Xu, Jiarui and Lin, Stephen and Wei, Fangyun and Hu, Han}, | |
| booktitle={Proceedings of the IEEE International Conference on Computer Vision Workshops}, | |
| pages={0--0}, | |
| year={2019} | |
| } | |
| ``` | |
| ## Results and models | |
| ### Cityscapes | |
| | Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | download | | |
| |--------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | |
| | GCNet | R-50-D8 | 512x1024 | 40000 | 5.8 | 3.93 | 77.69 | 78.56 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436-4b0fd17b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_40k_cityscapes/gcnet_r50-d8_512x1024_40k_cityscapes_20200618_074436.log.json) | | |
| | GCNet | R-101-D8 | 512x1024 | 40000 | 9.2 | 2.61 | 78.28 | 79.34 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436-5e62567f.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_40k_cityscapes/gcnet_r101-d8_512x1024_40k_cityscapes_20200618_074436.log.json) | | |
| | GCNet | R-50-D8 | 769x769 | 40000 | 6.5 | 1.67 | 78.12 | 80.09 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814-a26f4471.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_40k_cityscapes/gcnet_r50-d8_769x769_40k_cityscapes_20200618_182814.log.json) | | |
| | GCNet | R-101-D8 | 769x769 | 40000 | 10.5 | 1.13 | 78.95 | 80.71 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550-ca4f0a84.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_40k_cityscapes/gcnet_r101-d8_769x769_40k_cityscapes_20200619_092550.log.json) | | |
| | GCNet | R-50-D8 | 512x1024 | 80000 | - | - | 78.48 | 80.01 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450-ef8f069b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x1024_80k_cityscapes/gcnet_r50-d8_512x1024_80k_cityscapes_20200618_074450.log.json) | | |
| | GCNet | R-101-D8 | 512x1024 | 80000 | - | - | 79.03 | 79.84 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450-778ebf69.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x1024_80k_cityscapes/gcnet_r101-d8_512x1024_80k_cityscapes_20200618_074450.log.json) | | |
| | GCNet | R-50-D8 | 769x769 | 80000 | - | - | 78.68 | 80.66 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516-4839565b.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_769x769_80k_cityscapes/gcnet_r50-d8_769x769_80k_cityscapes_20200619_092516.log.json) | | |
| | GCNet | R-101-D8 | 769x769 | 80000 | - | - | 79.18 | 80.71 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628-8e043423.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_769x769_80k_cityscapes/gcnet_r101-d8_769x769_80k_cityscapes_20200619_092628.log.json) | | |
| ### ADE20K | |
| | Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | download | | |
| |--------|----------|-----------|--------:|----------|----------------|------:|--------------:|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | |
| | GCNet | R-50-D8 | 512x512 | 80000 | 8.5 | 23.38 | 41.47 | 42.85 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146-91a6da41.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_80k_ade20k/gcnet_r50-d8_512x512_80k_ade20k_20200614_185146.log.json) | | |
| | GCNet | R-101-D8 | 512x512 | 80000 | 12 | 15.20 | 42.82 | 44.54 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811-c3fcb6dd.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_80k_ade20k/gcnet_r101-d8_512x512_80k_ade20k_20200615_020811.log.json) | | |
| | GCNet | R-50-D8 | 512x512 | 160000 | - | - | 42.37 | 43.52 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122-d95f3e1f.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_160k_ade20k/gcnet_r50-d8_512x512_160k_ade20k_20200615_224122.log.json) | | |
| | GCNet | R-101-D8 | 512x512 | 160000 | - | - | 43.69 | 45.21 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406-615528d7.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_160k_ade20k/gcnet_r101-d8_512x512_160k_ade20k_20200615_225406.log.json) | | |
| ### Pascal VOC 2012 + Aug | |
| | Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | download | | |
| |--------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| | |
| | GCNet | R-50-D8 | 512x512 | 20000 | 5.8 | 23.35 | 76.42 | 77.51 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701-3cbfdab1.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_20k_voc12aug/gcnet_r50-d8_512x512_20k_voc12aug_20200617_165701.log.json) | | |
| | GCNet | R-101-D8 | 512x512 | 20000 | 9.2 | 14.80 | 77.41 | 78.56 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713-6c720aa9.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_20k_voc12aug/gcnet_r101-d8_512x512_20k_voc12aug_20200617_165713.log.json) | | |
| | GCNet | R-50-D8 | 512x512 | 40000 | - | - | 76.24 | 77.63 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105-9797336d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r50-d8_512x512_40k_voc12aug/gcnet_r50-d8_512x512_40k_voc12aug_20200613_195105.log.json) | | |
| | GCNet | R-101-D8 | 512x512 | 40000 | - | - | 77.84 | 78.59 | [model](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806-1e38208d.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/gcnet/gcnet_r101-d8_512x512_40k_voc12aug/gcnet_r101-d8_512x512_40k_voc12aug_20200613_185806.log.json) | | |