# STaDA: Style Transfer as Data Augmentation

arXiv: https://arxiv.org/abs/1909.01056 · HTML: https://mlsanity.com/paper/1909.01056/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2019.

## Built on by (most cited first, 21 of 21)

- [EnvEdit: Environment Editing for Vision-and-Language Navigation](https://mlsanity.com/paper/2203.15685/) (2022)
- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Image Data Augmentation Approaches: A Comprehensive Survey and Future directions](https://mlsanity.com/paper/2301.02830/) (2023)
- [Sill-Net: Feature Augmentation with Separated Illumination Representation](https://mlsanity.com/paper/2102.03539/) (2021)
- [An Empirical Study and Analysis on Open-Set Semi-Supervised Learning](https://mlsanity.com/paper/2101.08237/) (2021)
- [StyleTime: Style Transfer for Synthetic Time Series Generation](https://mlsanity.com/paper/2209.11306/) (2022)
- [Controllable Data Augmentation Through Deep Relighting](https://mlsanity.com/paper/2110.13996/) (2021)
- [Long Tail Image Generation Through Feature Space Augmentation and Iterated Learning](https://mlsanity.com/paper/2405.01705/) (2024)
- [Tackling Data Bias in Painting Classification with Style Transfer](https://mlsanity.com/paper/2301.02524/) (2023)
- [Contrastive Visual Data Augmentation](https://mlsanity.com/paper/2502.17709/) (2025)
- [SITTA: Single Image Texture Translation for Data Augmentation](https://mlsanity.com/paper/2106.13804/) (2021)
- [SASSL: Enhancing Self-Supervised Learning via Neural Style Transfer](https://mlsanity.com/paper/2312.01187/) (2023)
- [WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image Classification](https://mlsanity.com/paper/2308.14995/) (2023)
- [Analyzing the effectiveness of image augmentations for face recognition from limited data](https://mlsanity.com/paper/2105.08796/) (2021)
- [Non-Parametric Neural Style Transfer](https://mlsanity.com/paper/2108.12847/) (2021)
- [Generative Sentiment Transfer via Adaptive Masking](https://mlsanity.com/paper/2302.12045/) (2023)
- [Personal Protective Equipment Detection in Extreme Construction Conditions](https://mlsanity.com/paper/2307.13654/) (2023)
- [SDNIA-YOLO: A Robust Object Detection Model for Extreme Weather Conditions](https://mlsanity.com/paper/2406.12395/) (2024)
- [A Survey of Text Style Transfer: Applications and Ethical Implications](https://mlsanity.com/paper/2407.16737/) (2024)
- [ST-SACLF: Style Transfer Informed Self-Attention Classifier for Bias-Aware Painting Classification](https://mlsanity.com/paper/2408.01827/) (2024)
- [Evaluation of Randomization through Style Transfer for Enhanced Domain Generalization](https://mlsanity.com/paper/2604.05616/) (2026)

## Abstract (arXiv)

The success of training deep Convolutional Neural Networks (CNNs) heavily depends on a significant amount of labelled data. Recent research has found that neural style transfer algorithms can apply the artistic style of one image to another image without changing the latter's high-level semantic content, which makes it feasible to employ neural style transfer as a data augmentation method to add more variation to the training dataset. The contribution of this paper is a thorough evaluation of the effectiveness of the neural style transfer as a data augmentation method for image classification tasks. We explore the state-of-the-art neural style transfer algorithms and apply them as a data augmentation method on Caltech 101 and Caltech 256 dataset, where we found around 2% improvement from 83% to 85% of the image classification accuracy with VGG16, compared with traditional data augmentation strategies. We also combine this new method with conventional data augmentation approaches to further improve the performance of image classification. This work shows the potential of neural style transfer in computer vision field, such as helping us to reduce the difficulty of collecting sufficient labelled data and improve the performance of generic image-based deep learning algorithms.