DeepAI AI Chat
Log In Sign Up

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

06/04/2021
by   Shin'ya Yamaguchi, et al.
0

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 (CIFAR, TinyImageNet, STL-10, CelebA, and ImageNet).

READ FULL TEXT

page 1

page 8

page 12

page 13

page 14

03/20/2021

Are High-Frequency Components Beneficial for Training of Generative Adversarial Networks

Advancements in Generative Adversarial Networks (GANs) have the ability ...
10/04/2020

Spatial Frequency Bias in Convolutional Generative Adversarial Networks

As the success of Generative Adversarial Networks (GANs) on natural imag...
01/20/2020

Recovering Geometric Information with Learned Texture Perturbations

Regularization is used to avoid overfitting when training a neural netwo...
03/12/2022

Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation

Remarkable achievements have been attained with Generative Adversarial N...
11/07/2021

A-PixelHop: A Green, Robust and Explainable Fake-Image Detector

A novel method for detecting CNN-generated images, called Attentive Pixe...
12/17/2014

High Frequency Content based Stimulus for Perceptual Sharpness Assessment in Natural Images

A blind approach to evaluate the perceptual sharpness present in a natur...
05/29/2019

Stabilizing GANs with Octave Convolutions

In this preliminary report, we present a simple but very effective techn...