# Style transfer-based image synthesis as an efficient regularization technique in deep learning

arXiv: https://arxiv.org/abs/1905.10974 · HTML: https://mlsanity.com/paper/1905.10974/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 May 2019.

## Built on by (most cited first, 8 of 8)

- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Learning domain-agnostic visual representation for computational pathology using medically-irrelevant style transfer augmentation](https://mlsanity.com/paper/2102.01678/) (2021)
- [Semantic Perturbations with Normalizing Flows for Improved Generalization](https://mlsanity.com/paper/2108.07958/) (2021)
- [Managing Household Waste through Transfer Learning](https://mlsanity.com/paper/2402.09437/) (2024)
- [Man versus Machine: AutoML and Human Experts' Role in Phishing Detection](https://mlsanity.com/paper/2108.12193/) (2021)
- [MDT-Net: Multi-domain Transfer by Perceptual Supervision for Unpaired Images in OCT Scan](https://mlsanity.com/paper/2203.06363/) (2022)
- [Mapping of Land Use and Land Cover (LULC) using EuroSAT and Transfer Learning](https://mlsanity.com/paper/2401.02424/) (2023)
- [Neural Style Transfer for Synthesising a Dataset of Ancient Egyptian Hieroglyphs](https://mlsanity.com/paper/2504.02163/) (2025)

## Abstract (arXiv)

These days deep learning is the fastest-growing area in the field of Machine Learning. Convolutional Neural Networks are currently the main tool used for image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this paper, we have focused on the most frequently mentioned problem in the field of machine learning, that is relatively poor generalization abilities. Partial remedies for this are regularization techniques e.g. dropout, batch normalization, weight decay, transfer learning, early stopping and data augmentation. In this paper, we have focused on data augmentation. We propose to use a method based on a neural style transfer, which allows generating new unlabeled images of a high perceptual quality that combine the content of a base image with the appearance of another one. In a proposed approach, the newly created images are described with pseudo-labels, and then used as a training dataset. Real, labeled images are divided into the validation and test set. We validated the proposed method on a challenging skin lesion classification case study. Four representative neural architectures are examined. Obtained results show the strong potential of the proposed approach.