2020-07-07 20:52:19 +08:00
# Deep High-Resolution Representation Learning for Human Pose Estimation
## Introduction
2020-10-07 19:50:16 +08:00
2021-04-25 00:58:59 +08:00
<!-- [ALGORITHM] -->
2021-01-11 13:35:09 +08:00
2021-09-28 16:25:37 +08:00
< a href = "https://github.com/HRNet/HRNet-Semantic-Segmentation" > Official Repo< / a >
< a href = "https://github.com/open-mmlab/mmsegmentation/blob/v0.17.0/mmseg/models/backbones/hrnet.py#L218" > Code Snippet< / a >
2021-11-30 20:34:45 +08:00
## Abstract
2021-12-14 19:12:56 +08:00
<!-- [ABSTRACT] -->
2021-11-30 20:34:45 +08:00
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a low-resolution representation through a subnetwork that is formed by connecting high-to-low resolution convolutions \emph{in series} (e.g., ResNet, VGGNet), and then recover the high-resolution representation from the encoded low-resolution representation. Instead, our proposed network, named as High-Resolution Network (HRNet), maintains high-resolution representations through the whole process. There are two key characteristics: (i) Connect the high-to-low resolution convolution streams \emph{in parallel}; (ii) Repeatedly exchange the information across resolutions. The benefit is that the resulting representation is semantically richer and spatially more precise. We show the superiority of the proposed HRNet in a wide range of applications, including human pose estimation, semantic segmentation, and object detection, suggesting that the HRNet is a stronger backbone for computer vision problems. All the codes are available at [this https URL ](https://github.com/HRNet ).
<!-- [IMAGE] -->
< div align = center >
< img src = "https://user-images.githubusercontent.com/24582831/142901680-64c285bc-669f-4924-b054-46a2f07c5427.png" width = "80%" / >
< / div >
2021-09-28 16:25:37 +08:00
< details >
< summary align = "right" > < a href = "https://arxiv.org/abs/1908.07919" > HRNet (CVPR'2019)< / a > < / summary >
2020-10-07 19:50:16 +08:00
```latext
2020-07-07 20:52:19 +08:00
@inproceedings {SunXLW19,
title={Deep High-Resolution Representation Learning for Human Pose Estimation},
author={Ke Sun and Bin Xiao and Dong Liu and Jingdong Wang},
booktitle={CVPR},
year={2019}
}
```
2021-09-28 16:25:37 +08:00
< / details >
2020-07-07 20:52:19 +08:00
## Results and models
### Cityscapes
2020-10-07 19:50:16 +08:00
2021-04-10 05:36:03 +08:00
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ---------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| FCN | HRNetV2p-W18-Small | 512x1024 | 40000 | 1.7 | 23.74 | 73.86 | 75.91 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x1024_40k_cityscapes.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216-93db27d0.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_40k_cityscapes/fcn_hr18s_512x1024_40k_cityscapes_20200601_014216.log.json ) |
| FCN | HRNetV2p-W18 | 512x1024 | 40000 | 2.9 | 12.97 | 77.19 | 78.92 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x1024_40k_cityscapes.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216-f196fb4e.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_40k_cityscapes/fcn_hr18_512x1024_40k_cityscapes_20200601_014216.log.json ) |
| FCN | HRNetV2p-W48 | 512x1024 | 40000 | 6.2 | 6.42 | 78.48 | 79.69 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x1024_40k_cityscapes.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240-a989b146.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_40k_cityscapes/fcn_hr48_512x1024_40k_cityscapes_20200601_014240.log.json ) |
| FCN | HRNetV2p-W18-Small | 512x1024 | 80000 | - | - | 75.31 | 77.48 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x1024_80k_cityscapes.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700-1462b75d.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_80k_cityscapes/fcn_hr18s_512x1024_80k_cityscapes_20200601_202700.log.json ) |
| FCN | HRNetV2p-W18 | 512x1024 | 80000 | - | - | 78.65 | 80.35 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x1024_80k_cityscapes.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255-4e7b345e.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_80k_cityscapes/fcn_hr18_512x1024_80k_cityscapes_20200601_223255.log.json ) |
| FCN | HRNetV2p-W48 | 512x1024 | 80000 | - | - | 79.93 | 80.72 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x1024_80k_cityscapes.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606-58ea95d6.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_80k_cityscapes/fcn_hr48_512x1024_80k_cityscapes_20200601_202606.log.json ) |
| FCN | HRNetV2p-W18-Small | 512x1024 | 160000 | - | - | 76.31 | 78.31 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x1024_160k_cityscapes.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901-4a0797ea.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x1024_160k_cityscapes/fcn_hr18s_512x1024_160k_cityscapes_20200602_190901.log.json ) |
| FCN | HRNetV2p-W18 | 512x1024 | 160000 | - | - | 78.80 | 80.74 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x1024_160k_cityscapes.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822-221e4a4f.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x1024_160k_cityscapes/fcn_hr18_512x1024_160k_cityscapes_20200602_190822.log.json ) |
| FCN | HRNetV2p-W48 | 512x1024 | 160000 | - | - | 80.65 | 81.92 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x1024_160k_cityscapes.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946-59b7973e.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x1024_160k_cityscapes/fcn_hr48_512x1024_160k_cityscapes_20200602_190946.log.json ) |
2020-07-07 20:52:19 +08:00
### ADE20K
2020-10-07 19:50:16 +08:00
2021-04-10 05:36:03 +08:00
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| FCN | HRNetV2p-W18-Small | 512x512 | 80000 | 3.8 | 38.66 | 31.38 | 32.45 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_80k_ade20k.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345-77fc814a.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_ade20k/fcn_hr18s_512x512_80k_ade20k_20200614_144345.log.json ) |
2021-09-03 00:44:51 +08:00
| FCN | HRNetV2p-W18 | 512x512 | 80000 | 4.9 | 22.57 | 36.27 | 37.28 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_80k_ade20k.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910-6c9382c0.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_ade20k/fcn_hr18_512x512_80k_ade20k_20210827_114910.log.json ) |
2021-04-10 05:36:03 +08:00
| FCN | HRNetV2p-W48 | 512x512 | 80000 | 8.2 | 21.23 | 41.90 | 43.27 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_80k_ade20k.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946-7ba5258d.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_ade20k/fcn_hr48_512x512_80k_ade20k_20200614_193946.log.json ) |
2021-09-03 00:44:51 +08:00
| FCN | HRNetV2p-W18-Small | 512x512 | 160000 | - | - | 33.07 | 34.56 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_160k_ade20k.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739-f1e7c2e7.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_160k_ade20k/fcn_hr18s_512x512_160k_ade20k_20210829_174739.log.json ) |
2021-04-10 05:36:03 +08:00
| FCN | HRNetV2p-W18 | 512x512 | 160000 | - | - | 36.79 | 38.58 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_160k_ade20k.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426-ca961836.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_160k_ade20k/fcn_hr18_512x512_160k_ade20k_20200614_214426.log.json ) |
| FCN | HRNetV2p-W48 | 512x512 | 160000 | - | - | 42.02 | 43.86 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_160k_ade20k.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407-a52fc02c.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_160k_ade20k/fcn_hr48_512x512_160k_ade20k_20200614_214407.log.json ) |
2020-07-07 20:52:19 +08:00
### Pascal VOC 2012 + Aug
2020-10-07 19:50:16 +08:00
2021-04-10 05:36:03 +08:00
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ------ | ------------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
2021-09-03 00:44:51 +08:00
| FCN | HRNetV2p-W18-Small | 512x512 | 20000 | 1.8 | 43.36 | 65.5 | 68.89 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_20k_voc12aug.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910-0aceadb4.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_20k_voc12aug/fcn_hr18s_512x512_20k_voc12aug_20210829_174910.log.json ) |
2021-04-10 05:36:03 +08:00
| FCN | HRNetV2p-W18 | 512x512 | 20000 | 2.9 | 23.48 | 72.30 | 74.71 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_20k_voc12aug.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503-488d45f7.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_20k_voc12aug/fcn_hr18_512x512_20k_voc12aug_20200617_224503.log.json ) |
| FCN | HRNetV2p-W48 | 512x512 | 20000 | 6.2 | 22.05 | 75.87 | 78.58 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_20k_voc12aug.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419-89de05cd.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_20k_voc12aug/fcn_hr48_512x512_20k_voc12aug_20200617_224419.log.json ) |
| FCN | HRNetV2p-W18-Small | 512x512 | 40000 | - | - | 66.61 | 70.00 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_40k_voc12aug.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648-4f8d6e7f.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_40k_voc12aug/fcn_hr18s_512x512_40k_voc12aug_20200614_000648.log.json ) |
| FCN | HRNetV2p-W18 | 512x512 | 40000 | - | - | 72.90 | 75.59 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_40k_voc12aug.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401-1b4b76cd.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_40k_voc12aug/fcn_hr18_512x512_40k_voc12aug_20200613_224401.log.json ) |
| FCN | HRNetV2p-W48 | 512x512 | 40000 | - | - | 76.24 | 78.49 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_40k_voc12aug.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111-1b0f18bc.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_40k_voc12aug/fcn_hr48_512x512_40k_voc12aug_20200613_222111.log.json ) |
2020-09-22 14:56:13 +08:00
### Pascal Context
2020-10-07 19:50:16 +08:00
2021-04-10 05:36:03 +08:00
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ------ | ------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| FCN | HRNetV2p-W48 | 480x480 | 40000 | 6.1 | 8.86 | 45.14 | 47.42 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_480x480_40k_pascal_context.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context_20200911_164852-667d00b0.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context/fcn_hr48_480x480_40k_pascal_context-20200911_164852.log.json ) |
| FCN | HRNetV2p-W48 | 480x480 | 80000 | - | - | 45.84 | 47.84 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_480x480_80k_pascal_context.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context_20200911_155322-847a6711.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context/fcn_hr48_480x480_80k_pascal_context-20200911_155322.log.json ) |
2021-04-20 12:20:54 +08:00
### Pascal Context 59
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ------ | ------------ | --------- | ------: | -------- | -------------- | ----: | ------------: | ----------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| FCN | HRNetV2p-W48 | 480x480 | 40000 | - | - | 50.33 | 52.83 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_480x480_40k_pascal_context_59.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59_20210410_122738-b808b8b2.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_40k_pascal_context_59/fcn_hr48_480x480_40k_pascal_context_59-20210410_122738.log.json ) |
| FCN | HRNetV2p-W48 | 480x480 | 80000 | - | - | 51.12 | 53.56 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_480x480_80k_pascal_context_59.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59_20210411_003240-3ae7081e.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_480x480_80k_pascal_context_59/fcn_hr48_480x480_80k_pascal_context_59-20210411_003240.log.json ) |
2021-11-24 19:41:19 +08:00
2021-11-26 01:40:29 +08:00
### LoveDA
2021-11-24 19:41:19 +08:00
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
2021-12-14 19:49:24 +08:00
| FCN | HRNetV2p-W18-Small | 512x512 | 80000 | 1.59 | 24.87 | 49.28 | 49.42 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_80k_loveda.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228-60a86a7a.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_loveda/fcn_hr18s_512x512_80k_loveda_20211210_203228.log.json ) |
| FCN | HRNetV2p-W18 | 512x512 | 80000 | 2.76 | 12.92 | 50.81 | 50.95 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_80k_loveda.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952-93d9c3b3.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_loveda/fcn_hr18_512x512_80k_loveda_20211210_203952.log.json ) |
| FCN | HRNetV2p-W48 | 512x512 | 80000 | 6.20 | 9.61 | 51.42 | 51.64 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_80k_loveda.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756-67072f55.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_loveda/fcn_hr48_512x512_80k_loveda_20211211_044756.log.json ) |
2022-01-18 14:15:15 +08:00
### Potsdam
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
| ---------- | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | -------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| FCN | HRNetV2p-W18-Small | 512x512 | 80000 | 1.58 | 36.00 | 77.64 | 78.8 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18s_512x512_80k_potsdam.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517-ba32af63.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18s_512x512_80k_potsdam/fcn_hr18s_512x512_80k_potsdam_20211218_205517.log.json ) |
| FCN | HRNetV2p-W18 | 512x512 | 80000 | 2.76 | 19.25 | 78.26 | 79.24 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr18_512x512_80k_potsdam.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517-5d0387ad.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr18_512x512_80k_potsdam/fcn_hr18_512x512_80k_potsdam_20211218_205517.log.json ) |
| FCN | HRNetV2p-W48 | 512x512 | 80000 | 6.20 | 16.42 | 78.39 | 79.34 | [config ](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/hrnet/fcn_hr48_512x512_80k_potsdam.py ) | [model ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601-97434c78.pth ) | [log ](https://download.openmmlab.com/mmsegmentation/v0.5/hrnet/fcn_hr48_512x512_80k_potsdam/fcn_hr48_512x512_80k_potsdam_20211219_020601.log.json ) |
