Frustratingly Simple Domain Generalization via Image Stylization

19 Jun 2020  ·  Nathan Somavarapu, Chih-Yao Ma, Zsolt Kira ·

Convolutional Neural Networks (CNNs) show impressive performance in the standard classification setting where training and testing data are drawn i.i.d. from a given domain. However, CNNs do not readily generalize to new domains with different statistics, a setting that is simple for humans. In this work, we address the Domain Generalization problem, where the classifier must generalize to an unknown target domain. Inspired by recent works that have shown a difference in biases between CNNs and humans, we demonstrate an extremely simple yet effective method, namely correcting this bias by augmenting the dataset with stylized images. In contrast with existing stylization works, which use external data sources such as art, we further introduce a method that is entirely in-domain using no such extra sources of data. We provide a detailed analysis as to the mechanism by which the method works, verifying our claim that it changes the shape/texture bias, and demonstrate results surpassing or comparable to the state of the arts that utilize much more complex methods.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Domain Generalization PACS DGIS (Resnet-18, Painting) Average Accuracy 84.64 # 47
Domain Generalization PACS DGIS (Alexnet, Painting) Average Accuracy 76.62 # 91

Methods


No methods listed for this paper. Add relevant methods here