On Feature Normalization and Data Augmentation

25 Feb 2020Boyi LiFelix WuSer-Nam LimSerge BelongieKilian Q. Weinberger

Modern neural network training relies heavily on data augmentation for improved generalization. After the initial success of label-preserving augmentations, there has been a recent surge of interest in label-perturbing approaches, which combine features and labels across training samples to smooth the learned decision surface... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Domain Generalization ImageNet-A CutMix+MoEx (ResNet-50) Top-1 accuracy % 8.4 # 1

Methods used in the Paper