https://github.com/junjun2016/dmnet

Dynamic Multi-scale Filters for Semantic Segmentation (DMNet ICCV'2019)
https://github.com/junjun2016/dmnet

ade20k cityscapes dcm dfn dmnet dynamic-conv-module dynamic-filter dynamic-filter-generation dynamic-filter-network dynamic-multiscale-filters mmsegmentation semantic-segmentation

Last synced: about 2 months ago
JSON representation

Dynamic Multi-scale Filters for Semantic Segmentation (DMNet ICCV'2019)

Host: GitHub
URL: https://github.com/junjun2016/dmnet
Owner: Junjun2016
License: apache-2.0
Created: 2021-08-28T21:01:24.000Z (about 4 years ago)
Default Branch: main
Last Pushed: 2021-08-28T21:26:49.000Z (about 4 years ago)
Last Synced: 2025-07-27T22:49:07.630Z (3 months ago)
Topics: ade20k, cityscapes, dcm, dfn, dmnet, dynamic-conv-module, dynamic-filter, dynamic-filter-generation, dynamic-filter-network, dynamic-multiscale-filters, mmsegmentation, semantic-segmentation
Language: Python
Homepage: https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf
Size: 428 KB
Stars: 27
Watchers: 1
Forks: 3
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

README

          # Dynamic Multi-scale Filters for Semantic Segmentation (DMNet ICCV'2019)

## Introduction

Official implementation of **Dynamic Multi-scale Filters for Semantic Segmentation** ([Paper](https://openaccess.thecvf.com/content_ICCV_2019/papers/He_Dynamic_Multi-Scale_Filters_for_Semantic_Segmentation_ICCV_2019_paper.pdf)).  

🔥🔥 DMNet is on [MMsegmentation](https://github.com/open-mmlab/mmsegmentation/tree/master/configs/dmnet). 🔥🔥 

```latex

@InProceedings{He_2019_ICCV,

author = {He, Junjun and Deng, Zhongying and Qiao, Yu},

title = {Dynamic Multi-Scale Filters for Semantic Segmentation},

booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},

month = {October},

year = {2019}

}

```

## Overview

### Framework

![image](images/dcm.png)

## Results and models

### Cityscapes

| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                    | download                                                                                                                                                                                                                                                                                                                                               |

| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | ------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |

| DMNet  | R-50-D8  | 512x1024  |   40000 | 7.0      | 3.66           | 77.78 |         79.14 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes_20201215_042326-615373cf.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_40k_cityscapes/dmnet_r50-d8_512x1024_40k_cityscapes-20201215_042326.log.json)     |

| DMNet  | R-101-D8 | 512x1024  |   40000 | 10.6     | 2.54           | 78.37 |         79.72 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes_20201215_043100-8291e976.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_40k_cityscapes/dmnet_r101-d8_512x1024_40k_cityscapes-20201215_043100.log.json) |

| DMNet  | R-50-D8  | 769x769   |   40000 | 7.9      | 1.57           | 78.49 |         80.27 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r50-d8_769x769_40k_cityscapes.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes_20201215_093706-e7f0e23e.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_40k_cityscapes/dmnet_r50-d8_769x769_40k_cityscapes-20201215_093706.log.json)         |

| DMNet  | R-101-D8 | 769x769   |   40000 | 12.0     | 1.01           | 77.62 |         78.94 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r101-d8_769x769_40k_cityscapes.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes_20201215_081348-a74261f6.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_40k_cityscapes/dmnet_r101-d8_769x769_40k_cityscapes-20201215_081348.log.json)     |

| DMNet  | R-50-D8  | 512x1024  |   80000 | -        | -              | 79.07 |         80.22 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes_20201215_053728-3c8893b9.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x1024_80k_cityscapes/dmnet_r50-d8_512x1024_80k_cityscapes-20201215_053728.log.json)     |

| DMNet  | R-101-D8 | 512x1024  |   80000 | -        | -              | 79.64 |         80.67 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes_20201215_031718-fa081cb8.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x1024_80k_cityscapes/dmnet_r101-d8_512x1024_80k_cityscapes-20201215_031718.log.json) |

| DMNet  | R-50-D8  | 769x769   |   80000 | -        | -              | 79.22 |         80.55 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r50-d8_769x769_80k_cityscapes.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes_20201215_034006-6060840e.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_769x769_80k_cityscapes/dmnet_r50-d8_769x769_80k_cityscapes-20201215_034006.log.json)         |

| DMNet  | R-101-D8 | 769x769   |   80000 | -        | -              | 79.19 |         80.65 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r101-d8_769x769_80k_cityscapes.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes_20201215_082810-7f0de59a.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_769x769_80k_cityscapes/dmnet_r101-d8_769x769_80k_cityscapes-20201215_082810.log.json)     |

### ADE20K

| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) |  mIoU | mIoU(ms+flip) | config                                                                                                                | download                                                                                                                                                                                                                                                                                                                               |

| ------ | -------- | --------- | ------: | -------- | -------------- | ----: | ------------: | --------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |

| DMNet  | R-50-D8  | 512x512   |   80000 | 9.4      | 20.95          | 42.37 |         43.62 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r50-d8_512x512_80k_ade20k.py)   | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k_20201215_144744-f89092a6.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_80k_ade20k/dmnet_r50-d8_512x512_80k_ade20k-20201215_144744.log.json)         |

| DMNet  | R-101-D8 | 512x512   |   80000 | 13.0     | 13.88          | 45.34 |         46.13 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r101-d8_512x512_80k_ade20k.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k_20201215_104812-bfa45311.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_80k_ade20k/dmnet_r101-d8_512x512_80k_ade20k-20201215_104812.log.json)     |

| DMNet  | R-50-D8  | 512x512   |  160000 | -        | -              | 43.15 |         44.17 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r50-d8_512x512_160k_ade20k.py)  | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k_20201215_115313-025ab3f9.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r50-d8_512x512_160k_ade20k/dmnet_r50-d8_512x512_160k_ade20k-20201215_115313.log.json)     |

| DMNet  | R-101-D8 | 512x512   |  160000 | -        | -              | 45.42 |         46.76 | [config](https://github.com/open-mmlab/mmsegmentation/blob/master/configs/dmnet/dmnet_r101-d8_512x512_160k_ade20k.py) | [model](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k_20201215_111145-a0bc02ef.pth) | [log](https://download.openmmlab.com/mmsegmentation/v0.5/dmnet/dmnet_r101-d8_512x512_160k_ade20k/dmnet_r101-d8_512x512_160k_ade20k-20201215_111145.log.json) |

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

https://github.com/junjun2016/dmnet

Awesome Lists containing this project

README