Dynamic Multi-scale Filters for Semantic Segmentation (DMNet ICCV’2019)
Introduction
Official implementation of Dynamic Multi-scale Filters for Semantic Segmentation (Paper).
?
?
DMNet is on MMsegmentation.
?
?
@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
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 | 512×1024 | 40000 | 7.0 | 3.66 | 77.78 | 79.14 | config | model | log |
| DMNet | R-101-D8 | 512×1024 | 40000 | 10.6 | 2.54 | 78.37 | 79.72 | config | model | log |
| DMNet | R-50-D8 | 769×769 | 40000 | 7.9 | 1.57 | 78.49 | 80.27 | config | model | log |
| DMNet | R-101-D8 | 769×769 | 40000 | 12.0 | 1.01 | 77.62 | 78.94 | config | model | log |
| DMNet | R-50-D8 | 512×1024 | 80000 | – | – | 79.07 | 80.22 | config | model | log |
| DMNet | R-101-D8 | 512×1024 | 80000 | – | – | 79.64 | 80.67 | config | model | log |
| DMNet | R-50-D8 | 769×769 | 80000 | – | – | 79.22 | 80.55 | config | model | log |
| DMNet | R-101-D8 | 769×769 | 80000 | – | – | 79.19 | 80.65 | config | model | log |
ADE20K
| Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
|---|---|---|---|---|---|---|---|---|---|
| DMNet | R-50-D8 | 512×512 | 80000 | 9.4 | 20.95 | 42.37 | 43.62 | config | model | log |
| DMNet | R-101-D8 | 512×512 | 80000 | 13.0 | 13.88 | 45.34 | 46.13 | config | model | log |
| DMNet | R-50-D8 | 512×512 | 160000 | – | – | 43.15 | 44.17 | config | model | log |
| DMNet | R-101-D8 | 512×512 | 160000 | – | – | 45.42 | 46.76 | config | | log |
