School of
Information Technology and Electrical Engineering

Speaker: Tianren Wang
Seminar Date: Fri, 16/08/2019 - 11:00
Venue: 50-S201
Host: Prof Brian Lovell

Seminar Type:  MPhil Confirmation Seminar

Abstract: 

The image to image translation problem aims to translate an image from one domain to another. The problem has gained popularity as it can be a solution for deploying computer vision systems into a domain that is different from the training data domain. Recently, Generative Adversarial Network (GAN) has become an important and promising tool for solving image translation tasks. This project will utilize disentangled representation learning and GAN to translate samples from one domain to another. Once disentangled, the representations are disentangled into several factors (i.e. face identity, gender, etc). Unfortunately, training the representation requires labels for each factor. When the labels are not available, the learning process resorts to the latent space assumption which defines the existence of a common shared latent space between two domains. Often this assumption is ineffective as there is no explicit definition of the latent space. Therefore, this project will study the explicit form of such a latent space to make the learning process more accurate and faster. Furthermore, we propose to disentangle the unnecessary feature entanglements while simultaneously keeping the useful entanglement by classifying the features hierarchically. In this way, we can keep the high-level content-related feature entanglements while disentangling the low-level feature entanglements.

Biography: 

Tianren Wang is currently a first-year Masters student in the Data Science Group at UQ, under the supervision of Prof Brian Lovell and Dr Arnold Wiliem.  Tianren’s research interests mainly focus on AI, disentanglement, and domain adaption.