Top-1 Accuracy (%): 70.82
Papers with Code · CC BY-SA 4.0
Knowledge Distillation
Knowledge distillation is the process of transferring knowledge from a large model to a smaller one. While large models (such as very deep neural networks or ensembles of many models) have higher knowledge capacity than small models, this capacity might not be fully utilized.
논문
Top-1 accuracy %: 86.43model size: 87MCRD training setting: ✘
Top-1 accuracy %: 82.7model size: 22MCRD training setting: ✘
Top-1 accuracy %: 82.9model size: 22MCRD training setting: ✘
Top-1 Accuracy (%): 70.67
Top-1 accuracy %: 78.79model size: 56.9MCRD training setting: ✘
Top-1 accuracy %: 82.5
Top-1 accuracy %: 82.1model size: 22MCRD training setting: ✘
Top-1 Accuracy (%): 71.56
Top-1 accuracy %: 82.3model size: 29MCRD training setting: ✘
Top-1 accuracy %: 81.33
RMSE: 2.4315model size: 17.6M
Top-1 Accuracy (%): 71.88