What Can Style Transfer and Paintings Do For Model Robustness?

Hubert Lin, Mitchell van Zuijlen, Sylvia C. Pont, Maarten W.A. Wijntjes, Kavita Bala

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

4 Citations (Scopus)
37 Downloads (Pure)

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. Code and data are available at: https://github.com/hubertsgithub/style_painting_robustness
Original languageEnglish
Title of host publicationProceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
Subtitle of host publicationProceedings
Place of PublicationPiscataway
PublisherIEEE
Pages11023-11032
Number of pages10
ISBN (Electronic)978-1-6654-4509-2
ISBN (Print)978-1-6654-4510-8
DOIs
Publication statusPublished - 2021
Event2021 IEEE/CVF Conference on Computer Vision
and Pattern Recognition
- Virtual at Nashville, United States
Duration: 20 Jun 202125 Jun 2021

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)1063-6919

Conference

Conference2021 IEEE/CVF Conference on Computer Vision
and Pattern Recognition
Abbreviated titleCVPR 2021
Country/TerritoryUnited States
CityVirtual at Nashville
Period20/06/2125/06/21

Bibliographical note

Accepted Author Manuscript

Fingerprint

Dive into the research topics of 'What Can Style Transfer and Paintings Do For Model Robustness?'. Together they form a unique fingerprint.

Cite this