Scene Recognition on Places 205
14.9Top-1 AccuracySupervised
Evaluation results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| Supervisedarchitecture=ResNet-50, pretrained_dataset=ImageNet-1M, pretrained_epochs=2002020.05 | 14.9 | 21 | 26.9 | 32.1 | 36 | |
| PCL v2architecture=ResNet-50-MLP, pretrained_dataset=ImageNet-1M, pretrained_epochs=2002020.05 | 12.5 | 17.5 | 23.2 | 28.1 | 32.3 | |
| PCLarchitecture=ResNet-50, pretrained_dataset=ImageNet-1M, pretrained_epochs=2002020.05 | 11.3 | 15.7 | 19.5 | 24.1 | 28.4 | |
| MoCo v2architecture=ResNet-50-MLP, pretrained_dataset=ImageNet-1M, pretrained_epochs=2002020.05 | 10.9 | 16.3 | 20.8 | 26 | 30.1 | |
| SimCLRarchitecture=ResNet-50-MLP, pretrained_dataset=ImageNet-1M, pretrained_epochs=2002020.05 | 9.4 | 14.2 | 19.3 | 23.7 | 28.3 | |
| MoCoarchitecture=ResNet-50, pretrained_dataset=ImageNet-1M, pretrained_epochs=2002020.05 | 8.8 | 13.2 | 18.2 | 23.2 | 28 | |
| Jigsawarchitecture=ResNet-50, pretrained_dataset=ImageNet-14M2020.05 | 4.6 | 6.4 | 9.4 | 12.9 | 17.4 | |
| Randomarchitecture=ResNet-50, pretrained_dataset=ImageNet-1M, pretrained_epochs=2002020.05 | 0.7 | 0.7 | 0.7 | 0.7 | 0.7 |