Object Detection on COCO (APb, APb_50)
52.5APbGraphScan-Mamba-B
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| GraphScan-Mamba-BBackbone=GraphScan-Mamba-B, #P=112M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 52.5 | 73.2 | |
| GraphScan-Mamba-SBackbone=GraphScan-Mamba-S, #P=69M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 52 | 72.8 | |
| GraphScan-Mamba-BBackbone=GraphScan-Mamba-B, #P=112M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 51.9 | 73 | |
| DAMamba-BBackbone=DAMamba-B, #P=105M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 51.4 | 72.3 | |
| DAMamba-SBackbone=DAMamba-S, #P=65M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 51.2 | 72.1 | |
| GraphScan-Mamba-TBackbone=GraphScan-Mamba-T, #P=47M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 51 | 71.9 | |
| GraphScan-Mamba-SBackbone=GraphScan-Mamba-S, #P=69M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 50.7 | 72.1 | |
| DAMamba-BBackbone=DAMamba-B, #P=105M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 50.6 | 71.9 | |
| Spatial-Mamba-SBackbone=Spatial-Mamba-S, #P=63M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 50.5 | 71.5 | |
| DAMamba-TBackbone=DAMamba-T, #P=45M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 50.4 | 71.4 | |
| Spatial-Mamba-BBackbone=Spatial-Mamba-B, #P=115M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 50.4 | 71.8 | |
| VMamba-SBackbone=VMamba-S, #P=70M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 49.9 | 70.9 | |
| LocalVMamba-SBackbone=LocalVMamba-S, #P=69M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 49.9 | 70.5 | |
| DAMamba-SBackbone=DAMamba-S, #P=65M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 49.8 | 71.2 | |
| Spatial-Mamba-TBackbone=Spatial-Mamba-T, #P=46M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 49.3 | 70.7 | |
| Spatial-Mamba-SBackbone=Spatial-Mamba-S, #P=63M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 49.2 | 70.8 | |
| VMamba-BBackbone=VMamba-B, #P=108M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 49.2 | 71.4 | |
| GraphScan-Mamba-TBackbone=GraphScan-Mamba-T, #P=47M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 49.1 | 70.9 | |
| VMamba-TBackbone=VMamba-T, #P=50M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 48.8 | 70.4 | |
| VSSD-TBackbone=VSSD-T, #P=44M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 48.8 | 70.4 | |
| LocalVMamba-TBackbone=LocalVMamba-T, #P=45M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 48.7 | 70.1 | |
| VMamba-SBackbone=VMamba-S, #P=70M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 48.7 | 70 | |
| BiFormer-BBackbone=BiFormer-B, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 48.6 | 70.5 | |
| Swin-BBackbone=Swin-B, #P=107M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 48.6 | 70 | |
| DAMamba-TBackbone=DAMamba-T, #P=45M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 48.5 | 70.3 | |
| ConvNeXt-BBackbone=ConvNeXt-B, #P=107M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 48.5 | 70.1 | |
| NAT-SBackbone=NAT-S, #P=70M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 48.4 | 69.8 | |
| LocalVMamba-SBackbone=LocalVMamba-S, #P=69M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 48.4 | 69.9 | |
| VSSD-SBackbone=VSSD-S, #P=59M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 48.4 | 70.1 | |
| MSVMamba-TBackbone=MSVMamba-T, #P=53M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 48.3 | 69.5 | |
| Swin-SBackbone=Swin-S, #P=69M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 48.2 | 69.8 | |
| ConvNeXt-SBackbone=ConvNeXt-S, #P=70M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 47.9 | 70 | |
| BiFormer-SBackbone=BiFormer-S, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 47.8 | 69.8 | |
| NAT-TBackbone=NAT-T, #P=48M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 47.7 | 69 | |
| GroupMamba-TBackbone=GroupMamba-T, #P=40M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 47.6 | 69.8 | |
| Spatial-Mamba-TBackbone=Spatial-Mamba-T, #P=46M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 47.6 | 69.6 | |
| VMamba-TBackbone=VMamba-T, #P=50M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 47.3 | 69.3 | |
| ConvNeXt-BBackbone=ConvNeXt-B, #P=107M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 47 | 69.4 | |
| MSVMamba-TBackbone=MSVMamba-T, #P=53M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 46.9 | 68.8 | |
| VSSD-TBackbone=VSSD-T, #P=44M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 46.9 | 69.4 | |
| Swin-BBackbone=Swin-B, #P=107M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 46.9 | 69.2 | |
| LocalVMamba-TBackbone=LocalVMamba-T, #P=45M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 46.7 | 68.7 | |
| ConvNeXt-TBackbone=ConvNeXt-T, #P=48M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 46.2 | 67.9 | |
| Swin-TBackbone=Swin-T, #P=48M, Schedule=3x+MS, Detector framework=Mask R-CNN2026.05 | 46 | 68.1 | |
| ConvNeXt-SBackbone=ConvNeXt-S, #P=70M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 45.4 | 67.9 | |
| Swin-SBackbone=Swin-S, #P=69M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 44.8 | 68.6 | |
| ConvNeXt-TBackbone=ConvNeXt-T, #P=48M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 44.2 | 66.6 | |
| Swin-TBackbone=Swin-T, #P=48M, Schedule=1x, Detector framework=Mask R-CNN2026.05 | 42.7 | 65.2 |