Dense Pose Estimation on DensePose-COCO (minival)
68APDP-RCNN-DeepLab* (R101)
Evaluation results
| Method | Links | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| DP-RCNN-DeepLab* (R101)Backbone=ResNet-101, Training Protocol=CSE, Architecture=Optimized with DeepLab head, LBO size M=256, embedding size D=16, Loss=L_sigma2020.11 | 68 | 94.1 | 80 | 61.9 | 69.4 | 74.3 | 97.1 | 85.5 | 63.8 | 75 | |
| DP-RCNN-DeepLab* (R101)Backbone=ResNet-101, Training Protocol=IUV, Architecture=Optimized with DeepLab head2020.11 | 67.7 | 93.5 | 79.7 | 62.6 | 69.1 | 73.6 | 96.5 | 84.7 | 64.2 | 74.2 | |
| DP-RCNN* (R101)Backbone=ResNet-101, Training Protocol=CSE, Architecture=Optimized, LBO size M=256, embedding size D=16, Loss=L_sigma2020.11 | 67 | 93.8 | 78.6 | 60.1 | 68.3 | 72.8 | 96.4 | 83.7 | 61.5 | 73.6 | |
| DP-RCNN-DeepLab* (R50)Backbone=ResNet-50, Training Protocol=IUV, Architecture=Optimized with DeepLab head2020.11 | 66.8 | 92.8 | 79.7 | 60.7 | 68 | 72.1 | 95.8 | 82.9 | 62.2 | 72.4 | |
| DP-RCNN-DeepLab* (R50)Backbone=ResNet-50, Training Protocol=CSE, Architecture=Optimized with DeepLab head, LBO size M=256, embedding size D=16, Loss=L_sigma2020.11 | 66.6 | 93.8 | 77.6 | 60.8 | 67.7 | 72.8 | 96.5 | 83.1 | 62.1 | 73.5 | |
| DP-RCNN* (R101)Backbone=ResNet-101, Training Protocol=IUV, Architecture=Optimized2020.11 | 66.4 | 92.9 | 77.9 | 60.6 | 67.5 | 71.9 | 95.5 | 82.6 | 62.1 | 72.6 | |
| DP-RCNN* (R50)Backbone=ResNet-50, Training Protocol=CSE, Architecture=Optimized, LBO size M=256, embedding size D=16, Loss=L_sigma2020.11 | 66.1 | 92.5 | 78.2 | 58.7 | 67.4 | 71.7 | 95.5 | 82.4 | 60.3 | 72.5 | |
| DP-RCNN* (R50)Backbone=ResNet-50, Training Protocol=IUV, Architecture=Optimized2020.11 | 65.3 | 92.5 | 77.1 | 58.6 | 66.6 | 71.1 | 95.3 | 82 | 60.1 | 71.9 | |
| Parsing-RCNNTraining Protocol=IUV2020.11 | 65 | 93 | 78 | 56 | 67 | — | — | — | — | — | |
| AMA-netTraining Protocol=IUV2020.11 | 64.1 | 91.4 | 72.9 | 59.3 | 65.3 | 71.6 | 94.7 | 79.8 | 61.3 | 72.3 | |
| DP-RCNN (R101)Backbone=ResNet-101, Training Protocol=IUV2020.11 | 56.1 | 90.4 | 64.4 | 49.2 | 57.4 | 62.8 | 93.7 | 72.4 | 50.1 | 63.6 | |
| DP-RCNN (R50)Backbone=ResNet-50, Training Protocol=IUV2020.11 | 54.9 | 89.8 | 62.2 | 47.8 | 56.3 | 61.9 | 93.9 | 70.8 | 49.1 | 62.8 |