Fine Grained Image Classification On Caltech
Métriques
Top-1 Error Rate
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Top-1 Error Rate |
|---|---|
| understanding-gaussian-attention-bias-of | 9.798% |
| dead-pixel-test-using-effective-receptive | 4.42% |
| with-a-little-help-from-my-friends-nearest | 8.7% |
| stochastic-subsampling-with-average-pooling | 15.949% |
| spinalnet-deep-neural-network-with-gradual-1 | 2.68% |
| spinalnet-deep-neural-network-with-gradual-1 | 2.89% |
| bamboo-building-mega-scale-vision-dataset | - |
| on-the-ideal-number-of-groups-for-isometric | 22.247% |
| autoaugment-learning-augmentation-policies | 13.07% |
| vision-models-are-more-robust-and-fair-when | 9.0% |
| reduction-of-class-activation-uncertainty | 1.98% |
| a-continual-development-methodology-for-large | 4.06% |
| how-to-use-dropout-correctly-on-residual | 15.8036% |
| self-supervised-learning-by-estimating-twin-1 | 6.5% |
| progressivespinalnet-architecture-for-fc | - |
| an-evolutionary-approach-to-dynamic | 7% |
| unsupervised-learning-using-pretrained-cnn | - |
| spinalnet-deep-neural-network-with-gradual-1 | 6.84% |