Object Detection on MS COCO 2014 2017 (val)
52.9AP (Box)GC VIT-B
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| GC VIT-BBackbone=GC VIT-B, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=146, FLOPs (G)=10182022.06 | 52.9 | 71.7 | 57.8 | |
| ConvNeXt-BBackbone=ConvNeXt-B, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=146, FLOPs (G)=9642022.06 | 52.7 | 71.3 | 57.2 | |
| GC VIT-SBackbone=GC VIT-S, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=108, FLOPs (G)=8662022.06 | 52.4 | 71 | 57.1 | |
| Swin-SBackbone=Swin-S, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=107, FLOPs (G)=8382022.06 | 51.9 | 70.7 | 56.3 | |
| ConvNeXt-SBackbone=ConvNeXt-S, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=108, FLOPs (G)=8272022.06 | 51.9 | 70.8 | 56.5 | |
| Swin-BBackbone=Swin-B, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=145, FLOPs (G)=9822022.06 | 51.9 | 70.5 | 56.4 | |
| GC VIT-TBackbone=GC VIT-T, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=85, FLOPs (G)=7702022.06 | 51.6 | 70.4 | 56.1 | |
| Swin-TBackbone=Swin-T, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=86, FLOPs (G)=7452022.06 | 50.4 | 69.2 | 54.7 | |
| ConvNeXt-TBackbone=ConvNeXt-T, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=86, FLOPs (G)=7412022.06 | 50.4 | 69.1 | 54.8 | |
| X101-64Backbone=X101-64, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=140, FLOPs (G)=9722022.06 | 48.3 | 66.4 | 52.3 | |
| X101-32Backbone=X101-32, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=101, FLOPs (G)=8192022.06 | 48.1 | 66.5 | 52.4 | |
| DeiT-Small/16Backbone=DeiT-Small/16, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=80, FLOPs (G)=8892022.06 | 48 | 67.2 | 51.7 | |
| GC VIT-TBackbone=GC VIT-T, Framework=Mask R-CNN, Schedule=3x, Param (M)=48, FLOPs (G)=2912022.06 | 47.9 | 70.1 | 52.8 | |
| ResNet-50Backbone=ResNet-50, Framework=Cascade Mask R-CNN, Schedule=3x, Param (M)=82, FLOPs (G)=7392022.06 | 46.3 | 64.3 | 50.5 | |
| ConvNeXt-TBackbone=ConvNeXt-T, Framework=Mask R-CNN, Schedule=3x, Param (M)=48, FLOPs (G)=2622022.06 | 46.2 | 67.9 | 50.8 | |
| Swin-TBackbone=Swin-T, Framework=Mask R-CNN, Schedule=3x, Param (M)=48, FLOPs (G)=2672022.06 | 46 | 68.1 | 50.3 |