2023/07/21 by Mehmet Kerim Yucel, Ramazan Gökberk Cinbiş, Yucel, Mehmet Kerim +3 · 2 citations
Computer Science · Medicine · #Advanced Neural Network Applications #Anomaly Detection Techniques and Applications #Artificial Intelligence (cs.AI) #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences
paper · pdf · doi:10.48550/arxiv.2307.11823
openalex publication_date 2023/07/21 · openalex created_date 2023/07/26 · openalex updated_date 2026/07/28
Convolutional Neural Networks (CNN) are known to exhibit poor generalization performance under distribution shifts. Their generalization have been studied extensively, and one line of work approaches the problem from a frequency-centric perspective. These studies highlight the fact that humans and CNNs might focus on different frequency components of an image. First, inspired by these observations, we propose a simple yet effective data augmentation method HybridAugment that reduces the reliance of CNNs on high-frequency components, and thus improves their robustness while keeping their clean accuracy high. Second, we propose HybridAugment++, which is a hierarchical augmentation method that attempts to unify various frequency-spectrum augmentations. HybridAugment++ builds on HybridAugment, and also reduces the reliance of CNNs on the amplitude component of images, and promotes phase information instead. This unification results in competitive to or better than state-of-the-art results on clean accuracy (CIFAR-10/100 and ImageNet), corruption benchmarks (ImageNet-C, CIFAR-10-C and CIFAR-100-C), adversarial robustness on CIFAR-10 and out-of-distribution detection on various datasets. HybridAugment and HybridAugment++ are implemented in a few lines of code, does not require extra data, ensemble models or additional networks.