Style Augmentation: Data Augmentation via Style Randomization

09/14/2018
by   Philip T. Jackson, et al.
0

We introduce style augmentation, a new form of data augmentation based on random style transfer, for improving the robustness of convolutional neural networks (CNN) over both classification and regression based tasks. During training, our style augmentation randomizes texture, contrast and color, while preserving shape and semantic content. This is accomplished by adapting an arbitrary style transfer network to perform style randomization, by sampling input style embeddings from a multivariate normal distribution instead of inferring them from a style image. In addition to standard classification experiments, we investigate the effect of style augmentation (and data augmentation generally) on domain transfer tasks. We find that data augmentation significantly improves robustness to domain shift, and can be used as a simple, domain agnostic alternative to domain adaptation. Comparing style augmentation against a mix of seven traditional augmentation techniques, we find that it can be readily combined with them to improve network performance. We validate the efficacy of our technique with domain transfer experiments in classification and monocular depth estimation, illustrating consistent improvements in generalization.

READ FULL TEXT

page 2

page 5

page 6

page 10

research
02/02/2021

Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation

Suboptimal generalization of machine learning models on unseen data is a...
research
08/29/2023

WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image Classification

Currently, style augmentation is capturing attention due to convolutiona...
research
11/30/2020

What Can Style Transfer and Paintings Do For Model Robustness?

A common strategy for improving model robustness is through data augment...
research
01/06/2023

Tackling Data Bias in Painting Classification with Style Transfer

It is difficult to train classifiers on paintings collections due to mod...
research
01/22/2021

Rethinking Domain Generalization Baselines

Despite being very powerful in standard learning settings, deep learning...
research
11/23/2021

Multi-Modality Microscopy Image Style Transfer for Nuclei Segmentation

Annotating microscopy images for nuclei segmentation is laborious and ti...
research
09/16/2023

Enhancing Visual Perception in Novel Environments via Incremental Data Augmentation Based on Style Transfer

The deployment of autonomous agents in real-world scenarios is challenge...

Please sign up or login with your details

Forgot password? Click here to reset