ICML 2019

Similarity of Neural Network Representations Revisited

ICML 2019 google-research/google-research

We introduce a similarity index that measures the relationship between representational similarity matrices and does not suffer from this limitation.

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

ICML 2019 lukemelas/EfficientNet-PyTorch

Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available.

 SOTA for Image Classification on Stanford Cars (using extra training data)

FINE-GRAINED IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH TRANSFER LEARNING