TY - JOUR
AU1 - Yang, Qikai
AU2 - Ji, Cheng
AU3 - Luo, Huaiying
AU4 - Li, Panfeng
AU5 - Ding, Zhicheng
AB - Abstract:In this paper, we introduce a novel data augmentation technique that combines the advantages of style augmentation and random erasing by selectively replacing image subregions with style-transferred patches. Our approach first applies a random style transfer to training images, then randomly substitutes selected areas of these images with patches derived from the style-transferred versions. This method is able to seamlessly accommodate a wide range of existing style transfer algorithms and can be readily integrated into diverse data augmentation pipelines. By incorporating our strategy, the training process becomes more robust and less prone to overfitting. Comparative experiments demonstrate that, relative to previous style augmentation methods, our technique achieves superior performance and faster convergence.
TI - Data Augmentation Through Random Style Replacement
JF - Computing Research Repository
DO - 10.48550/arxiv.2504.10563
DA - 2025-04-14
UR - https://www.deepdyve.com/lp/arxiv-cornell-university/data-augmentation-through-random-style-replacement-ctl0Nj18Jf
VL - 2025
IS - 2504
DP - DeepDyve
ER -