2020-07-07 20:52:19 +08:00
|
|
|
# Fully Convolutional Networks for Semantic Segmentation
|
|
|
|
|
|
|
|
|
|
## Introduction
|
|
|
|
|
```
|
|
|
|
|
@article{shelhamer2017fully,
|
|
|
|
|
title={Fully convolutional networks for semantic segmentation},
|
|
|
|
|
author={Shelhamer, Evan and Long, Jonathan and Darrell, Trevor},
|
|
|
|
|
journal={IEEE transactions on pattern analysis and machine intelligence},
|
|
|
|
|
volume={39},
|
|
|
|
|
number={4},
|
|
|
|
|
pages={640--651},
|
|
|
|
|
year={2017},
|
|
|
|
|
publisher={IEEE Trans Pattern Anal Mach Intell}
|
|
|
|
|
}
|
|
|
|
|
```
|
|
|
|
|
|
|
|
|
|
## Results and models
|
|
|
|
|
|
|
|
|
|
### Cityscapes
|
|
|
|
|
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | download |
|
|
|
|
|
|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
|
|
|
| FCN | R-50-D8 | 512x1024 | 40000 | 5.7 | 4.17 | 72.25 | 73.36 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608-efe53f0d.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_40k_cityscapes/fcn_r50-d8_512x1024_40k_cityscapes_20200604_192608.log.json) |
|
|
|
|
|
| FCN | R-101-D8 | 512x1024 | 40000 | 9.2 | 2.66 | 75.45 | 76.58 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852-a883d3a1.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_40k_cityscapes/fcn_r101-d8_512x1024_40k_cityscapes_20200604_181852.log.json) |
|
|
|
|
|
| FCN | R-50-D8 | 769x769 | 40000 | 6.5 | 1.80 | 71.47 | 72.54 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104-977b5d02.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_40k_cityscapes/fcn_r50-d8_769x769_40k_cityscapes_20200606_113104.log.json) |
|
|
|
|
|
| FCN | R-101-D8 | 769x769 | 40000 | 10.4 | 1.19 | 73.93 | 75.14 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208-7d4ab69c.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_40k_cityscapes/fcn_r101-d8_769x769_40k_cityscapes_20200606_113208.log.json) |
|
|
|
|
|
| FCN | R-50-D8 | 512x1024 | 80000 | - | - | 73.61 | 74.24 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019-03aa804d.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x1024_80k_cityscapes/fcn_r50-d8_512x1024_80k_cityscapes_20200606_113019.log.json) |
|
|
|
|
|
| FCN | R-101-D8 | 512x1024 | 80000 | - | - | 75.13 | 75.94 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038-3fb937eb.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x1024_80k_cityscapes/fcn_r101-d8_512x1024_80k_cityscapes_20200606_113038.log.json) |
|
|
|
|
|
| FCN | R-50-D8 | 769x769 | 80000 | - | - | 72.64 | 73.32 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749-f5caeabc.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_769x769_80k_cityscapes/fcn_r50-d8_769x769_80k_cityscapes_20200606_195749.log.json) |
|
|
|
|
|
| FCN | R-101-D8 | 769x769 | 80000 | - | - | 75.52 | 76.61 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354-45cbac68.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_769x769_80k_cityscapes/fcn_r101-d8_769x769_80k_cityscapes_20200606_214354.log.json) |
|
|
|
|
|
|
|
|
|
|
### ADE20K
|
|
|
|
|
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | download |
|
|
|
|
|
|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
|
|
|
| FCN | R-50-D8 | 512x512 | 80000 | 8.5 | 23.49 | 35.94 | 37.94 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016-f8ac5082.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_80k_ade20k/fcn_r50-d8_512x512_80k_ade20k_20200614_144016.log.json) |
|
|
|
|
|
| FCN | R-101-D8 | 512x512 | 80000 | 12 | 14.78 | 39.61 | 40.83 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143-bc1809f7.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_80k_ade20k/fcn_r101-d8_512x512_80k_ade20k_20200615_014143.log.json) |
|
|
|
|
|
| FCN | R-50-D8 | 512x512 | 160000 | - | - | 36.10 | 38.08 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713-4edbc3b4.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_160k_ade20k/fcn_r50-d8_512x512_160k_ade20k_20200615_100713.log.json) |
|
|
|
|
|
| FCN | R-101-D8 | 512x512 | 160000 | - | - | 39.91 | 41.40 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816-fd192bd5.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_160k_ade20k/fcn_r101-d8_512x512_160k_ade20k_20200615_105816.log.json) |
|
|
|
|
|
|
|
|
|
|
### Pascal VOC 2012 + Aug
|
|
|
|
|
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | download |
|
|
|
|
|
|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
|
|
|
| FCN | R-50-D8 | 512x512 | 20000 | 5.7 | 23.28 | 67.08 | 69.94 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715-52dc5306.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_20k_voc12aug/fcn_r50-d8_512x512_20k_voc12aug_20200617_010715.log.json) |
|
|
|
|
|
| FCN | R-101-D8 | 512x512 | 20000 | 9.2 | 14.81 | 71.16 | 73.57 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842-0bb4e798.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_20k_voc12aug/fcn_r101-d8_512x512_20k_voc12aug_20200617_010842.log.json) |
|
|
|
|
|
| FCN | R-50-D8 | 512x512 | 40000 | - | - | 66.97 | 69.04 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222-5e2dbf40.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r50-d8_512x512_40k_voc12aug/fcn_r50-d8_512x512_40k_voc12aug_20200613_161222.log.json) |
|
|
|
|
|
| FCN | R-101-D8 | 512x512 | 40000 | - | - | 69.91 | 72.38 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240-4c8bcefd.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_512x512_40k_voc12aug/fcn_r101-d8_512x512_40k_voc12aug_20200613_161240.log.json) |
|
2020-09-22 14:56:13 +08:00
|
|
|
|
|
|
|
|
### Pascal Context
|
|
|
|
|
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | download |
|
|
|
|
|
|--------|----------|-----------|--------:|----------|----------------|------:|--------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
|
|
|
|
|
| FCN | R-101-D8 | 480x480 | 40000 | - | 9.93 | 44.14 | 45.67 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context_20200911_212515-9b565a6d.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_40k_pascal_context/fcn_r101-d8_480x480_40k_pascal_context-20200911_212515.log.json) |
|
|
|
|
|
| FCN | R-101-D8 | 480x480 | 80000 | - | - | 44.47 | 45.74 | [model](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context_20200915_032644-a3828480.pth) | [log](https://openmmlab.oss-accelerate.aliyuncs.com/mmsegmentation/v0.5/fcn/fcn_r101-d8_480x480_80k_pascal_context/fcn_r101-d8_480x480_80k_pascal_context-20200915_032644.log.json) |
|
