OneFormer (ConvNeXt-XL, multi-scale)

Reported on 2 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.

Medical1 result

Semantic SegmentationonCityscapes val
mIoU· 2022-11-10
84.6
best: 90.3 (EfficientPS (Cityscapes-fine))
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220

Audio1 result

10-shot image generationonCityscapes val
mIoU· 2022-11-10
84.6
best: 90.3 (EfficientPS (Cityscapes-fine))
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220