What Can Style Transfer and Paintings Do For Model Robustness?

TL;DR

This paper explores how style transfer and artist-created paintings can be used as data augmentation techniques to improve neural network robustness by encouraging invariance to textures and perceptual cues.

Contribution

It demonstrates that style transfer is effective even without paintings as style images and shows that paintings as data improve model robustness and induce different invariances.

Findings

Style transfer functions well without paintings as style images.

Learning from paintings enhances model robustness.

Models learn different invariances from stylization versus paintings.

Abstract

A common strategy for improving model robustness is through data augmentations. Data augmentations encourage models to learn desired invariances, such as invariance to horizontal flipping or small changes in color. Recent work has shown that arbitrary style transfer can be used as a form of data augmentation to encourage invariance to textures by creating painting-like images from photographs. However, a stylized photograph is not quite the same as an artist-created painting. Artists depict perceptually meaningful cues in paintings so that humans can recognize salient components in scenes, an emphasis which is not enforced in style transfer. Therefore, we study how style transfer and paintings differ in their impact on model robustness. First, we investigate the role of paintings as style images for stylization-based data augmentation. We find that style transfer functions well even without paintings as style images. Second, we show that learning from paintings as a form of perceptual data augmentation can improve model robustness. Finally, we investigate the invariances learned from stylization and from paintings, and show that models learn different invariances from these differing forms of data. Our results provide insights into how stylization improves model robustness, and provide evidence that artist-created paintings can be a valuable source of data for model robustness.