Instance Segmentation on COCO (APm, APm50, APm75)
44.2APmVMamba-S
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| VMamba-SBackbone=VMamba-S, Schedule=3x MS, Architecture=Mask R-CNN, Params=70M, FLOPs=349G2024.01 | 44.2 | 68.2 | 47.7 | |
| VMamba-BBackbone=VMamba-B, Schedule=1x, Architecture=Mask R-CNN, Params=108M, FLOPs=485G2024.01 | 44.1 | 68.3 | 47.7 | |
| Vanilla-VMamba-SBackbone=Vanilla-VMamba-S, Schedule=3x MS, Architecture=Mask R-CNN, Params=64M, FLOPs=400G2024.01 | 44 | 67.6 | 47.3 | |
| VMamba-SBackbone=VMamba-S, Schedule=1x, Architecture=Mask R-CNN, Params=70M, FLOPs=349G2024.01 | 43.7 | 67.3 | 47 | |
| VMamba-TBackbone=VMamba-T, Schedule=3x MS, Architecture=Mask R-CNN, Params=50M, FLOPs=271G2024.01 | 43.7 | 67.4 | 47 | |
| Vanilla-VMamba-BBackbone=Vanilla-VMamba-B, Schedule=1x, Architecture=Mask R-CNN, Params=96M, FLOPs=540G2024.01 | 43.3 | 67.1 | 46.7 | |
| Vanilla-VMamba-TBackbone=Vanilla-VMamba-T, Schedule=3x MS, Architecture=Mask R-CNN, Params=42M, FLOPs=286G2024.01 | 43.2 | 66.9 | 46.4 | |
| Swin-SBackbone=Swin-S, Schedule=3x MS, Architecture=Mask R-CNN, Params=69M, FLOPs=354G2024.01 | 43.2 | 67 | 46.1 | |
| Vanilla-VMamba-SBackbone=Vanilla-VMamba-S, Schedule=1x, Architecture=Mask R-CNN, Params=64M, FLOPs=400G2024.01 | 43 | 66.6 | 46.4 | |
| ConvNeXt-SBackbone=ConvNeXt-S, Schedule=3x MS, Architecture=Mask R-CNN, Params=70M, FLOPs=348G2024.01 | 42.9 | 66.9 | 46.2 | |
| VMamba-TBackbone=VMamba-T, Schedule=1x, Architecture=Mask R-CNN, Params=50M, FLOPs=271G2024.01 | 42.7 | 66.4 | 45.9 | |
| ConvNeXt-BBackbone=ConvNeXt-B, Schedule=1x, Architecture=Mask R-CNN, Params=108M, FLOPs=486G2024.01 | 42.7 | 66.3 | 46 | |
| Swin-BBackbone=Swin-B, Schedule=1x, Architecture=Mask R-CNN, Params=107M, FLOPs=496G2024.01 | 42.3 | — | — | |
| Vanilla-VMamba-TBackbone=Vanilla-VMamba-T, Schedule=1x, Architecture=Mask R-CNN, Params=42M, FLOPs=286G2024.01 | 42.1 | 65.5 | 45.3 | |
| ConvNeXt-SBackbone=ConvNeXt-S, Schedule=1x, Architecture=Mask R-CNN, Params=70M, FLOPs=348G2024.01 | 41.8 | 65.2 | 45.1 | |
| ConvNeXt-TBackbone=ConvNeXt-T, Schedule=3x MS, Architecture=Mask R-CNN, Params=48M, FLOPs=262G2024.01 | 41.7 | 65 | 44.9 | |
| Swin-TBackbone=Swin-T, Schedule=3x MS, Architecture=Mask R-CNN, Params=48M, FLOPs=267G2024.01 | 41.6 | 65.1 | 44.9 | |
| Swin-SBackbone=Swin-S, Schedule=1x, Architecture=Mask R-CNN, Params=69M, FLOPs=354G2024.01 | 40.9 | 63.4 | 44.2 | |
| ConvNeXt-TBackbone=ConvNeXt-T, Schedule=1x, Architecture=Mask R-CNN, Params=48M, FLOPs=262G2024.01 | 40.1 | 63.3 | 42.8 | |
| Swin-TBackbone=Swin-T, Schedule=1x, Architecture=Mask R-CNN, Params=48M, FLOPs=267G2024.01 | 39.3 | 62.2 | 42.2 |