[Apr 20th 2022] LabMeeting: How good is my GAN?

Barbara Toniella Corradini (University of Siena)

When: Apr 13th, 2022 – 11:00 – 11:45 AM
Where: Google meet link
Description

How good is my GAN?
Generative adversarial networks (GANs) are one of the most popular methods for generating images today. While impressive results have been validated by visual inspection, a number of quantitative criteria have emerged only recently. We argue here that the existing ones are insufficient and need to be in adequation with the task at hand. In this paper we introduce two measures based on image classification – GAN-train and GAN-test, which approximate the recall (diversity) and precision (quality of the image) of GANs respectively. We evaluate a number of recent GAN approaches based on these two measures and demon- strate a clear difference in performance. Furthermore, we observe that the increasing difficulty of the dataset, from CIFAR10 over CIFAR100 to ImageNet, shows an inverse correlation with the quality of the GANs, as clearly evident from our measures.

Paper by K. Shmelkov, C. Schmid, and K. Alahari

 |  Category: Seminars