Data Augmentation Through Random Style Replacement
This incremental improvement addresses robustness in image training for computer vision applications.
The paper tackles the problem of overfitting in image training by introducing a data augmentation technique that combines style transfer and random erasing, achieving superior performance and faster convergence compared to previous methods.
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.