DDRNet-23-slim

Reported on 6 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical3 results

Semantic SegmentationonCityscapes test
Time (ms)· 2021-01-15
9.8
best: 4000 (DeepLab)
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arXiv:2101.06085
Semantic SegmentationonCamVid
Time (ms)· 2021-01-15
4.3
best: 227 (Dilation10)
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arXiv:2101.06085
Semantic SegmentationonCamVid
mIoU· 2021-01-15
74.7
best: 82 (PIDNet-M (Cityscapes-Pretrained))
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arXiv:2101.06085

Audio3 results

10-shot image generationonCityscapes test
Time (ms)· 2021-01-15
9.8
best: 4000 (DeepLab)
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arXiv:2101.06085
10-shot image generationonCamVid
Time (ms)· 2021-01-15
4.3
best: 227 (Dilation10)
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arXiv:2101.06085
10-shot image generationonCamVid
mIoU· 2021-01-15
74.7
best: 82 (PIDNet-M (Cityscapes-Pretrained))
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arXiv:2101.06085