A Fast Knowledge Distillation Framework for Visual Recognition

Open paper
Benchmark Model Rank Results
image-classification-on-imagenetResNet-101 (224 res, Fast Knowledge Distillation)#577Top 1 Accuracy: 81.9%
image-classification-on-imagenetResNet-50 (224 res, Fast Knowledge Distillation)#683Top 1 Accuracy: 80.1%
image-classification-on-imagenetSReT-LT (Fast Knowledge Distillation)#767Top 1 Accuracy: 78.7%Number of params: 5MGFLOPs: 1.2

Rank counts only results with a code link.