You Only Need Half: Boosting Data Augmentation by Using Partial Content

TL;DR

YONA is a simple, parameter-free data augmentation method that improves neural network robustness by training on partially masked images, enhancing performance and adversarial resilience across various models and datasets.

Contribution

The paper introduces YONA, a novel data augmentation technique that uses partial image masking to improve robustness without additional computational cost.

Findings

YONA enhances CIFAR classification accuracy.

YONA increases neural network resilience to adversarial attacks.

YONA outperforms traditional augmentation methods in some cases.

Abstract

We propose a novel data augmentation method termed You Only Need hAlf (YONA), which simplifies the augmentation process. YONA bisects an image, substitutes one half with noise, and applies data augmentation techniques to the remaining half. This method reduces the redundant information in the original image, encourages neural networks to recognize objects from incomplete views, and significantly enhances neural networks' robustness. YONA is distinguished by its properties of parameter-free, straightforward application, enhancing various existing data augmentation strategies, and thereby bolstering neural networks' robustness without additional computational cost. To demonstrate YONA's efficacy, extensive experiments were carried out. These experiments confirm YONA's compatibility with diverse data augmentation methods and neural network architectures, yielding substantial improvements in CIFAR classification tasks, sometimes outperforming conventional image-level data augmentation methods. Furthermore, YONA markedly increases the resilience of neural networks to adversarial attacks. Additional experiments exploring YONA's variants conclusively show that masking half of an image optimizes performance. The code is available at https://github.com/HansMoe/YONA.