OpenSeeD

Reported on 1 benchmark 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 Vision1 result

Instance SegmentationonADE20K val
AP· uses extra data· 2023-03-14
42.6
best: 44.2 (OneFormer (InternImage-H, emb_dim=1024, single-scale, 896x896, COCO-Pretrained))
A Simple Framework for Open-Vocabulary Segmentation and Detection arXiv:2303.08131