Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification

arXiv:2403.01944v1 Announce Type: cross
Abstract: Computer vision models normally witness degraded performance when deployed in real-world scenarios, due to unexpected changes in inputs that were not accounted for during training. Data augmentation is commonly used to address this issue, as it aims to increase data variety and reduce the distribution gap between training and test data. However, common visual augmentations might not guarantee extensive robustness of computer vision models. In this paper, we propose Auxiliary Fourier-basis Augmentation (AFA), a complementary …

abstract arxiv augmentation bridge classification computer computer vision cs.cv cs.lg data fourier functions gap image inputs issue normally performance reduce training type vision vision models witness world