DeepAI AI Chat
Log In Sign Up

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

by   Shin'ya Yamaguchi, et al.

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).


page 1

page 8

page 12

page 13

page 14


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

Advancements in Generative Adversarial Networks (GANs) have the ability ...

Spatial Frequency Bias in Convolutional Generative Adversarial Networks

As the success of Generative Adversarial Networks (GANs) on natural imag...

Recovering Geometric Information with Learned Texture Perturbations

Regularization is used to avoid overfitting when training a neural netwo...

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

Remarkable achievements have been attained with Generative Adversarial N...

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

A novel method for detecting CNN-generated images, called Attentive Pixe...

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

A blind approach to evaluate the perceptual sharpness present in a natur...

Stabilizing GANs with Octave Convolutions

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