LaU-regression-loss

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 SegmentationonADE20K val
mIoU· 2019-11-13
45.02
best: 62.8 (BEiT-3)
Location-aware Upsampling for Semantic Segmentation arXiv:1911.05250
Semantic SegmentationonADE20K
Test Score· 2019-11-13
56.32
best: 62.8 (Swin-L (UperNet, ImageNet-22k pretrain))
Location-aware Upsampling for Semantic Segmentation arXiv:1911.05250
Semantic SegmentationonADE20K
Validation mIoU· 2019-11-13
45.02
best: 63.6 (ViT-P (InternImage-H))
Location-aware Upsampling for Semantic Segmentation arXiv:1911.05250

Audio3 results

10-shot image generationonADE20K val
mIoU· 2019-11-13
45.02
best: 62.8 (BEiT-3)
Location-aware Upsampling for Semantic Segmentation arXiv:1911.05250
10-shot image generationonADE20K
Test Score· 2019-11-13
56.32
best: 62.8 (Swin-L (UperNet, ImageNet-22k pretrain))
Location-aware Upsampling for Semantic Segmentation arXiv:1911.05250
10-shot image generationonADE20K
Validation mIoU· 2019-11-13
45.02
best: 63.6 (ViT-P (InternImage-H))
Location-aware Upsampling for Semantic Segmentation arXiv:1911.05250