HRNetV2 (HRNetV2-W48)

Reported on 4 benchmarks across 2 tasks · 2 papers · 2 SOTA

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

Medical2 results

Semantic SegmentationonCityscapes val
mIoU· 2019-08-20
81.1
best: 90.3 (EfficientPS (Cityscapes-fine))
SOTA
Deep High-Resolution Representation Learning for Visual Recognition arXiv:1908.07919
Semantic SegmentationonADE20K val
mIoU· 2019-04-09
42.99
best: 62.8 (BEiT-3)
High-Resolution Representations for Labeling Pixels and Regions arXiv:1904.04514

Audio2 results

10-shot image generationonCityscapes val
mIoU· 2019-08-20
81.1
best: 90.3 (EfficientPS (Cityscapes-fine))
SOTA
Deep High-Resolution Representation Learning for Visual Recognition arXiv:1908.07919
10-shot image generationonADE20K val
mIoU· 2019-04-09
42.99
best: 62.8 (BEiT-3)
High-Resolution Representations for Labeling Pixels and Regions arXiv:1904.04514