# Cross-Domain Image Classification through Neural-Style Transfer Data Augmentation

arXiv: https://arxiv.org/abs/1910.05611 · HTML: https://mlsanity.com/paper/1910.05611/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2019.

## Built on by (most cited first, 2 of 2)

- [A survey of synthetic data augmentation methods in computer vision](https://mlsanity.com/paper/2403.10075/) (2024)
- [Style-Based Neural Architectures for Real-Time Weather Classification](https://mlsanity.com/paper/2604.18251/) (2026)

## Abstract (arXiv)

In particular, the lack of sufficient amounts of domain-specific data can reduce the accuracy of a classifier. In this paper, we explore the effects of style transfer-based data transformation on the accuracy of a convolutional neural network classifiers in the context of automobile detection under adverse winter weather conditions. The detection of automobiles under highly adverse weather conditions is a difficult task as such conditions present large amounts of noise in each image. The InceptionV2 architecture is trained on a composite dataset, consisting of either normal car image dataset , a mixture of normal and style transferred car images, or a mixture of normal car images and those taken at blizzard conditions, at a ratio of 80:20. All three classifiers are then tested on a dataset of car images taken at blizzard conditions and on vehicle-free snow landscape images. We evaluate and contrast the effectiveness of each classifier upon each dataset, and discuss the strengths and weaknesses of style-transfer based approaches to data augmentation.