EoMT (DINOv2-g, single-scale, 1280x1280, COCO pre-trained)

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· 2025-03-24
52.8
best: 54.5 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
Your ViT is Secretly an Image Segmentation Model arXiv:2503.19108

Audio1 result

10-shot image generationonADE20K val
PQ· uses extra data· 2025-03-24
52.8
best: 54.5 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
Your ViT is Secretly an Image Segmentation Model arXiv:2503.19108

Computer Vision1 result

Panoptic SegmentationonADE20K val
PQ· uses extra data· 2025-03-24
52.8
best: 54.5 (OneFormer (InternImage-H, emb_dim=256, single-scale, 896x896))
Your ViT is Secretly an Image Segmentation Model arXiv:2503.19108