Data Augmentation Through Random Style Replacement

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.

Accepted by 2025 6th International Conference on Computer Vision, Image and Deep Learning

References in corpus (7)

• Data Augmentation in Natural Language Processing: A Novel Text Generation Approach for Long and Short Text Classifiers
• Time Series Modeling for Heart Rate Prediction: From ARIMA to Transformers
• Deception Detection from Linguistic and Physiological Data Streams Using Bimodal Convolutional Neural Networks
• Regional Style and Color Transfer
• Evaluating Modern Approaches in 3D Scene Reconstruction: NeRF vs Gaussian-Based Methods
• A Comparative Study on Enhancing Prediction in Social Network Advertisement through Data Augmentation
• Enhance Image-to-Image Generation with LLaVA-generated Prompts