Mask2Former (Swin-L + FAPN)

Reported on 4 benchmarks across 1 task · 1 paper

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

Computer Vision4 results

Instance SegmentationonADE20K val
AP· 2021-12-02
33.4
best: 44.2 (OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained))
Masked-attention Mask Transformer for Universal Image Segmentation arXiv:2112.01527
Instance SegmentationonADE20K val
APL· 2021-12-02
54.6
best: 64.3 (OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained))
Masked-attention Mask Transformer for Universal Image Segmentation arXiv:2112.01527
Instance SegmentationonADE20K val
APM· 2021-12-02
37.6
best: 49.9 (OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained))
Masked-attention Mask Transformer for Universal Image Segmentation arXiv:2112.01527
Instance SegmentationonADE20K val
APS· 2021-12-02
14.6
best: 23.7 (OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained))
Masked-attention Mask Transformer for Universal Image Segmentation arXiv:2112.01527