Circumventing Outliers of AutoAugment with Knowledge Distillation

Open paper
Benchmark Model Rank Results
image-classification-on-imagenetKDforAA (EfficientNet-B8)#202Top 1 Accuracy: 85.8%Number of params: 88M
image-classification-on-imagenetKDforAA (EfficientNet-B7)#232Top 1 Accuracy: 85.5%Number of params: 66M

Rank counts only results with a code link.