DeepAI AI Chat
Log In Sign Up

Detecting GAN generated errors

by   Xiru Zhu, et al.
McGill University

Despite an impressive performance from the latest GAN for generating hyper-realistic images, GAN discriminators have difficulty evaluating the quality of an individual generated sample. This is because the task of evaluating the quality of a generated image differs from deciding if an image is real or fake. A generated image could be perfect except in a single area but still be detected as fake. Instead, we propose a novel approach for detecting where errors occur within a generated image. By collaging real images with generated images, we compute for each pixel, whether it belongs to the real distribution or generated distribution. Furthermore, we leverage attention to model long-range dependency; this allows detection of errors which are reasonable locally but not holistically. For evaluation, we show that our error detection can act as a quality metric for an individual image, unlike FID and IS. We leverage Improved Wasserstein, BigGAN, and StyleGAN to show a ranking based on our metric correlates impressively with FID scores. Our work opens the door for better understanding of GAN and the ability to select the best samples from a GAN model.


page 2

page 4

page 5

page 7


Detecting and Simulating Artifacts in GAN Fake Images

To detect GAN generated images, conventional supervised machine learning...

DAM-GAN : Image Inpainting using Dynamic Attention Map based on Fake Texture Detection

Deep neural advancements have recently brought remarkable image synthesi...

On the generalization of GAN image forensics

Recently the GAN generated face images are more and more realistic with ...

An Architecture for the detection of GAN-generated Flood Images with Localization Capabilities

In this paper, we address a new image forensics task, namely the detecti...

DA-FDFtNet: Dual Attention Fake Detection Fine-tuning Network to Detect Various AI-Generated Fake Images

Due to the advancement of Generative Adversarial Networks (GAN), Autoenc...

On the use of Benford's law to detect GAN-generated images

The advent of Generative Adversarial Network (GAN) architectures has giv...

Detecting GAN-generated Images by Orthogonal Training of Multiple CNNs

In the last few years, we have witnessed the rise of a series of deep le...