SimpleClick (ViT-H, C+L)

Reported on 3 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 Vision3 results

Interactive SegmentationonBerkeley
NoC@90· 2022-10-20
1.75
best: 5.6 (CM guidance)
SimpleClick: Interactive Image Segmentation with Simple Vision Transformers arXiv:2210.11006
Interactive SegmentationonDAVIS
NoC@85· 2022-10-20
3.41
best: 12.52 (DOS w/o GC)
SimpleClick: Interactive Image Segmentation with Simple Vision Transformers arXiv:2210.11006
Interactive SegmentationonDAVIS
NoC@90· 2022-10-20
4.7
best: 17.11 (DOS w/o GC)
SimpleClick: Interactive Image Segmentation with Simple Vision Transformers arXiv:2210.11006