Title

Image Generation by Back-Propagation on Input Using a Discriminator Network

Abstract

Abstract

In this thesis, we propose an image generation method that only involves a discriminator network; no generator or decoder networks are required. To generate an image, we iteratively apply an adversarial attack on the discriminator by updating the input image, which is noise at the beginning, to maximize the discriminator's output score. Generated images are then used as negative examples, together with the real images as positive examples, to fine-tune the discriminator. After several rounds of generation and fine-tuning, the generated images start to look real. To show the effectiveness of our method, we present promising results on MNIST, Yale Face, and EMNIST datasets. On MNIST, our FID score (28.8) is comparable to those of the state-of-the-art GANs.

Zoom Link:
https://zoom.us/j/93427656800?pwd=Rlk0YVRWS1JkeVFCc1VWdkI4NUYyUT09

Supervisor(s)

Supervisor(s)

MERVE TAPLI

Date and Location

Date and Location

2021-09-08 15:00:00

Category

Category

MSc_Thesis