DiffusionInst-SwinL

Reported on 2 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 Vision2 results

Instance SegmentationonCOCO test-dev
mask AP· 2022-12-06
48.3
best: 57.1 (Co-DETR)
DiffusionInst: Diffusion Model for Instance Segmentation arXiv:2212.02773
Instance SegmentationonLVIS v1.0 val
mask AP· 2022-12-06
38.6
best: 60.7 (Co-DETR (single-scale))
DiffusionInst: Diffusion Model for Instance Segmentation arXiv:2212.02773