Mask R-CNN (ViL Base, 1x lr)

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

Instance SegmentationonCOCO minival
AP50· 2021-03-29
67.2
best: 80.1 (InternImage-H)
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding arXiv:2103.15358
Instance SegmentationonCOCO minival
AP75· 2021-03-29
49.3
best: 62.8 (Co-DETR)
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding arXiv:2103.15358
Instance SegmentationonCOCO minival
mask AP· 2021-03-29
45.1
best: 56.6 (Co-DETR)
Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding arXiv:2103.15358