Image Classification on ImageNet (val) (Intermediate Feature Metrics)
56.5Feature Score (conv2)Krizhevsky et al.
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Krizhevsky et al.Training=labels, Input=rgb, Params=1.00, Feats=1.00, Runtime=1.002016.03 | 56.5 | 56.5 | 56.5 | 56.5 | |
| Noroozi & FavaroTraining=imagenet, Input=rgb, Params=1.00, Feats=5.60, Runtime=7.352016.03 | 56 | 52.4 | 48.3 | 38.1 | |
| Donahue et al.Training=imagenet, Input=rgb, Params=1.00, Feats=0.87, Runtime=0.962016.03 | 51.9 | 47.3 | 41.9 | 31.1 | |
| Krizhevsky et al.Training=labels, Input=L, Params=0.99, Feats=1.00, Runtime=0.922016.03 | 50.5 | 50.5 | 50.5 | 50.5 | |
| Doersch et al.Training=imagenet, Input=rgb, Params=1.61, Feats=1.00, Runtime=2.822016.03 | 47.6 | 48.7 | 45.6 | 30.4 | |
| Wang & GuptaTraining=videos, Input=rgb, Params=1.00, Feats=1.00, Runtime=1.002016.03 | 46.9 | 42.8 | 38.8 | 29.8 | |
| Colorful Image ColorizationTraining=imagenet, Input=L, Params=0.99, Feats=0.87, Runtime=0.842016.03 | 46.6 | 43.5 | 40.7 | 35.2 | |
| GaussianTraining=imagenet, Input=rgb, Params=1.00, Feats=1.00, Runtime=1.002016.03 | 41 | 34.8 | 27.1 | 12 |