PatchConvNet-B60 (UperNet)

Reported on 4 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.

Medical2 results

Semantic SegmentationonADE20K val
mIoU· 2021-12-27
51.1
best: 62.8 (BEiT-3)
Augmenting Convolutional networks with attention-based aggregation arXiv:2112.13692
Semantic SegmentationonADE20K
Validation mIoU· 2021-12-27
51.1
best: 63.6 (ViT-P (InternImage-H))
Augmenting Convolutional networks with attention-based aggregation arXiv:2112.13692

Audio2 results

10-shot image generationonADE20K val
mIoU· 2021-12-27
51.1
best: 62.8 (BEiT-3)
Augmenting Convolutional networks with attention-based aggregation arXiv:2112.13692
10-shot image generationonADE20K
Validation mIoU· 2021-12-27
51.1
best: 63.6 (ViT-P (InternImage-H))
Augmenting Convolutional networks with attention-based aggregation arXiv:2112.13692