Title

Image Generation Using Only a Discriminator Network with Gradient Norm Penalty

Abstract

Abstract

This thesis explores the idea of generating images using only a discriminator network by extending a previously proposed method (Tapli, 2021) in several ways. The base method works by iteratively updating the input image, which is pure noise at the beginning, while increasing the discriminator’s score. We extend the training procedure of the base network by adding the following new losses: (i) total variation, (ii) N-way classification (if labels are available), and (iii) gradient norm penalty on real examples. Our experiments show that while each of these modifications improves the base method, their combination results in a significantly better version. Using a mini convolutional network with, we achieve an FID score of 25.26 on the MNIST dataset. We demonstrate additional results on the EMNIST dataset and present results for out-of-distribution detection on FashionMNIST, EMNIST, and KMNIST datasets.

Supervisor(s)

Supervisor(s)

CANSU CEMRE YESILCIMEN

Date and Location

Date and Location

2022-09-02 10:00:00

Category

Category

MSc_Thesis