MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks

Open paper

Benchmark	Model	Rank	Results
image-classification-on-imagenet	MEAL V2 (ResNet-50) (380 res)	#591	Top 1 Accuracy: 81.72%Number of params: 25.6M
image-classification-on-imagenet	MEAL V2 (ResNet-50) (224 res)	#656	Top 1 Accuracy: 80.67%
image-classification-on-imagenet	ResNet-18 (MEAL V2)	#927	Top 1 Accuracy: 73.19%
image-classification-on-omnibenchmark	MEAL-V2	#11	Average Top-1 Accuracy: 36.6