# Style Augmentation: Data Augmentation via Style Randomization

arXiv: https://arxiv.org/abs/1809.05375 · HTML: https://mlsanity.com/paper/1809.05375/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Sep 2018.

## Built on by (most cited first, 30 of 79)

- [UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2104.05358/) (2021)
- [A Comprehensive Survey of Image Augmentation Techniques for Deep Learning](https://mlsanity.com/paper/2205.01491/) (2022)
- [EnvEdit: Environment Editing for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.15685/) (2022)
- [Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2108.11249/) (2021)
- [SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gap](https://mlsanity.com/paper/2110.03101/) (2021)
- [Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap](https://mlsanity.com/paper/2203.04275/) (2022)
- [Federated Domain Generalization for Image Recognition via Cross-Client Style Transfer](https://mlsanity.com/paper/2210.00912/) (2022)
- [Progressive Random Convolutions for Single Domain Generalization](https://mlsanity.com/paper/2304.00424/) (2023)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospects](https://mlsanity.com/paper/2305.07348/) (2023)
- [MaxStyle: Adversarial Style Composition for Robust Medical Image Segmentation](https://mlsanity.com/paper/2206.01737/) (2022)
- [CrossEarth: Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation](https://mlsanity.com/paper/2410.22629/) (2024)
- [Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation](https://mlsanity.com/paper/2102.01678/) (2021)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraints](https://mlsanity.com/paper/2212.12103/) (2022)
- [Learning to Adapt CLIP for Few-Shot Monocular Depth Estimation](https://mlsanity.com/paper/2311.01034/) (2023)
- [Not Just Pretty Pictures: Toward Interventional Data Augmentation Using Text-to-Image Generators](https://mlsanity.com/paper/2212.11237/) (2022)
- [Domain-Specificity Inducing Transformers for Source-Free Domain Adaptation](https://mlsanity.com/paper/2308.14023/) (2023)
- [An overview of mixing augmentation methods and augmentation strategies](https://mlsanity.com/paper/2107.09887/) (2021)
- [Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer](https://mlsanity.com/paper/2308.10601/) (2023)
- [Delving into Crispness: Guided Label Refinement for Crisp Edge Detection](https://mlsanity.com/paper/2306.15172/) (2023)
- [MRFP: Learning Generalizable Semantic Segmentation from Sim-2-Real with Multi-Resolution Feature Perturbation](https://mlsanity.com/paper/2311.18331/) (2023)
- [6D Object Pose Estimation from Approximate 3D Models for Orbital Robotics](https://mlsanity.com/paper/2303.13241/) (2023)
- [Data Augmentation Through Random Style Replacement](https://mlsanity.com/paper/2504.10563/) (2025)
- [Physical Knowledge Enhanced Deep Neural Network for Sea Surface Temperature Prediction](https://mlsanity.com/paper/2304.09376/) (2023)
- [Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2305.13752/) (2023)
- [Story Visualization by Online Text Augmentation with Context Memory](https://mlsanity.com/paper/2308.07575/) (2023)
- [An Empirical Study and Analysis on Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2101.08237/) (2021)
- [Learning to Generalize over Subpartitions for Heterogeneity-aware Domain Adaptive Nuclei Segmentation](https://mlsanity.com/paper/2401.09496/) (2024)
- [Bridging the Domain Gap for Flight-Ready Spaceborne Vision](https://mlsanity.com/paper/2409.11661/) (2024)

## Abstract (arXiv)

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.