You Only Need Half: Boosting Data Augmentation by Using Partial Content
This addresses the need for more robust neural networks in computer vision, though it is incremental as it builds on existing data augmentation strategies.
The paper tackles the problem of improving neural network robustness by proposing YONA, a data augmentation method that bisects images and applies augmentation to half, which enhances performance in CIFAR classification tasks and increases resilience to adversarial attacks, with results showing substantial improvements over conventional methods.
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.