CVLGIVJun 4, 2021

F-Drop&Match: GANs with a Dead Zone in the High-Frequency Domain

arXiv:2106.02343v22 citations
Originality Incremental advance
AI Analysis

This addresses a specific limitation in GANs for image generation, offering incremental improvements in frequency domain accuracy.

The paper tackles the problem of GANs failing to replicate high-frequency components in natural images by introducing F-Drop and F-Match training techniques, which improve generative performance on multiple image benchmarks.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes