CBNetV2 (Dual-Swin-L HTC, single-scale)
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
- box mAP· 2021-07-0159.4best: 66 (Co-DETR)
- box mAP· 2021-07-0159.4best: 66 (Co-DETR)
- box mAP· 2021-07-0159.4best: 66 (Co-DETR)
- box mAP· 2021-07-0159.4best: 66 (Co-DETR)
Computer Vision2 results
- box mAP· 2021-07-0159.4best: 66 (Co-DETR)
- mask AP· 2021-07-0151.6best: 57.1 (Co-DETR)