MogaNet-L (Mask R-CNN 1x)
Reported on 6 benchmarks across 6 tasks · 1 paper
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Methodology4 results
- AP· 2022-11-0749.4best: 72.2 (LOGO-CAP (Ours) HRNet-W48)
- AP· 2022-11-0749.4best: 61.8 (Mr. DETR (Swin-L, 1x, 5cale))
- AP· 2022-11-0749.4best: 61.8 (Mr. DETR (Swin-L, 1x, 5cale))
- AP· 2022-11-0749.4best: 61.8 (Mr. DETR (Swin-L, 1x, 5cale))
Computer Vision2 results
- AP· 2022-11-0749.4best: 61.8 (Mr. DETR (Swin-L, 1x, 5cale))
- mask AP· 2022-11-0744.1best: 57.1 (Co-DETR)