MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks. In NeurIPS 2020 workshop.
v1.0.0
MEAL ImageNet pre-trained models from
"MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks" https://arxiv.org/pdf/2009.08453.pdf "MEAL: Multi-Model Ensemble via Adversarial Learning" https://arxiv.org/pdf/1812.02425.pdf