Instance Segmentation on COCO mini 2017 (val)
35.6AP^maskDRConv-MaskRCNN 16R
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| DRConv-MaskRCNN 16RFramework=Mask R-CNN, Backbone=ResNet-50, Neck=FPN with DRConv, Region Number=16R2020.03 | 35.6 | 58 | 37.6 | |
| DRConv-MaskRCNN 8RFramework=Mask R-CNN, Backbone=ResNet-50, Neck=FPN with DRConv, Region Number=8R2020.03 | 35.5 | 57.6 | 37.6 | |
| DRConv-MaskRCNN 4RFramework=Mask R-CNN, Backbone=ResNet-50, Neck=FPN with DRConv, Region Number=4R2020.03 | 35.3 | 57.1 | 37.4 | |
| MaskRCNNFramework=Mask R-CNN, Backbone=ResNet-50, Neck=FPN2020.03 | 34.5 | 55.8 | 36.6 | |
| InsLocPre-training Epochs=2002021.02 | 23.5 | — | — | |
| InfoMinPre-training Epochs=2002021.02 | 21.7 | — | — | |
| SupervisedPre-training Epochs=902021.02 | 21.2 | — | — | |
| MoCo-v2Pre-training Epochs=2002021.02 | 21.1 | — | — | |
| BYOLPre-training Epochs=3002021.02 | 19.6 | — | — | |
| SimCLRPre-training Epochs=2002021.02 | 18.9 | — | — | |
| Relative Loc.Pre-training Epochs=2002021.02 | 16.1 | — | — | |
| SwAVPre-training Epochs=4002021.02 | 15.2 | — | — |