Texture-Aware Strategies for Subregion Style Transfer Augmentation
The paper proposes a new framework for data augmentation that prioritizes regions with strong texture responses for style replacement.
The paper introduces a novel texture-aware approach to style augmentation that prioritizes regions with strong texture responses.
Before reading this…
Applications
- →image classification
- →data augmentation
To understand this paper, make sure you know these concepts first:
- image classificationfind papers →
- data augmentationfind papers →
Abstract
More Like ThisA common strategy for data augmentation is to apply style transfer on training images to enrich appearance variations. Recent approaches have combined style augmentation with random erasing by selectively replacing image subregions with style-transferred patches. However, existing methods rely on uniformly random region selection or fixed geometric constraints, which may fail to cover informative texture patterns and limit augmentation diversity. To address these limitations, we propose a texture-aware subregion style augmentation framework that prioritizes regions with strong texture responses for style replacement. Furthermore, we extend this framework with a hybrid region strategy that combines a texture-driven region with an auxiliary random region, implicitly enabling more diverse style perturbations. Experiments demonstrate that our approach achieves higher classification accuracy and improves robustness compared with existing style-based augmentation methods.