2021/06/04 by Shin’ya Yamaguchi, Yamaguchi, Shin'ya, Sekitoshi Kanai +1 · 1 citation
Computer Science · #Advanced Data Storage Technologies #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Video Processing (eess.IV) #Machine Learning (cs.LG) #Neural Networks and Reservoir Computing #Speech Recognition and Synthesis #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2106.02343
openalex publication_date 2021/06/04 · openalex created_date 2024/04/11 · openalex updated_date 2026/07/28
Generative adversarial networks built from deep convolutional neural networks (GANs) lack the ability to exactly replicate the high-frequency components of natural images. To alleviate this issue, we introduce two novel training techniques called frequency dropping (F-Drop) and frequency matching (F-Match). The key idea of F-Drop is to filter out unnecessary high-frequency components from the input images of the discriminators. This simple modification prevents the discriminators from being confused by perturbations of the high-frequency components. In addition, F-Drop makes the GANs focus on fitting in the low-frequency domain, in which there are the dominant components of natural images. F-Match minimizes the difference between real and fake images in the frequency domain for generating more realistic images. F-Match is implemented as a regularization term in the objective functions of the generators; it penalizes the batch mean error in the frequency domain. F-Match helps the generators to fit in the high-frequency domain filtered out by F-Drop to the real image. We experimentally demonstrate that the combination of F-Drop and F-Match improves the generative performance of GANs in both the frequency and spatial domain on multiple image benchmarks.