DDRNet-23(Cityscapes-Pretrained)

Reported on 4 benchmarks across 2 tasks · 1 paper · 2 SOTA

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

Medical2 results

Semantic SegmentationonCamVid
mIoU· uses extra data· 2021-01-15
80.6
best: 82 (PIDNet-M (Cityscapes-Pretrained))
SOTA
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arXiv:2101.06085
Semantic SegmentationonCamVid
Time (ms)· uses extra data· 2021-01-15
10.6
best: 227 (Dilation10)
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arXiv:2101.06085

Audio2 results

10-shot image generationonCamVid
mIoU· uses extra data· 2021-01-15
80.6
best: 82 (PIDNet-M (Cityscapes-Pretrained))
SOTA
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arXiv:2101.06085
10-shot image generationonCamVid
Time (ms)· uses extra data· 2021-01-15
10.6
best: 227 (Dilation10)
Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes arXiv:2101.06085