OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained)

Reported on 4 benchmarks across 1 task · 1 paper · 4 SOTA

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· 2022-11-10
44.2
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Instance SegmentationonADE20K val
APL· 2022-11-10
64.3
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Instance SegmentationonADE20K val
APM· 2022-11-10
49.9
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220
Instance SegmentationonADE20K val
APS· 2022-11-10
23.7
SOTA
OneFormer: One Transformer to Rule Universal Image Segmentation arXiv:2211.06220