OpenSeed(SwinL, single scale, 1280x1280)

Reported on 3 benchmarks across 3 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 SegmentationonADE20K val
PQ· uses extra data· 2023-03-14
53.7
best: 54.5 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
A Simple Framework for Open-Vocabulary Segmentation and Detection arXiv:2303.08131

Audio1 result

10-shot image generationonADE20K val
PQ· uses extra data· 2023-03-14
53.7
best: 54.5 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
A Simple Framework for Open-Vocabulary Segmentation and Detection arXiv:2303.08131

Computer Vision1 result

Panoptic SegmentationonADE20K val
PQ· uses extra data· 2023-03-14
53.7
best: 54.5 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
A Simple Framework for Open-Vocabulary Segmentation and Detection arXiv:2303.08131