FourierAugment: Frequency-Based Image Encoding for Resource-Constrained Vision Tasks

Jiae Yoon, Myeongjin Lee, Ue-Hwan Kim

Primary Area: representation learning for computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Fourier Analysis, Computer Vision, Few-Shot Class Incremental Learning, Resource-Constrained Models

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: Resource-constrained vision tasks, such as image classification on low-end devices, put forward significant challenges due to limited computational resources and restricted access to a vast number of training samples. Previous studies have utilized data augmentation that optimizes various image transformations to learn effective lightweight models with few data samples. However, these studies require a calibration step for optimizing data augmentation to specific scenarios or hardly exploit frequency components readily available from Fourier analysis. To address the limitations, we propose a frequency-based image encoding method, namely FourierAugment, which allows lightweight models to learn richer features with a restrained amount of data. Further, we reveal the correlations between the amount of data and frequency components lightweight models learn in the process of designing FourierAugment. Extensive experiments on multiple resource-constrained vision tasks under diverse conditions corroborate the effectiveness of the proposed FourierAugment method compared to baselines.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2163