Congratulations to Harry Yang for passing his defense on May 7, 2019! Let us hear what he would like to say about his defense and an abstract of his thesis.
“In the thesis, we tackle the problem of translating faces and bodies between different identities without paired training data: we cannot directly train a translation module using supervised signals in this case. Instead, we propose to train a conditional variational auto-encoder (CVAE) to disentangle different latent factors such as identity and expressions. In order to achieve effective disentanglement, we further use multi-view information such as keypoints and facial landmarks to train multiple CVAEs. By relying on these simplified representations of the data we are using a more easily disentangled representation to guide the disentanglement of image itself. Experiments demonstrate the effectiveness of our method in multiple face and body datasets. We also show that our model is a more robust image classifier and adversarial example detector comparing with traditional multi-class neural networks.
“To address the issue of scaling to new identities and also generate better-quality results, we further propose an alternative approach that uses self-supervised learning based on StyleGAN to factorize out different attributes of face images, such as hair color, facial expressions, skin color, and others. Using pre-trained StyleGAN combined with iterative style inference we can easily manipulate the facial expressions or combine the facial expressions of any two people, without the need of training a specific new model for each of the identity involved. This is one of the first scalable and high-quality approach for generating DeepFake data, which serves as a critical first step to learn a more robust and general classifier against adversarial examples.”
Harry also shared about his Ph.D. experience:
“Firstly, I would like to express my heartfelt thanks to Professor Kuo, who has always been the kindest and most generous towards the students, and also provided the best guidance and training during my PhD. I am also thankful to all the lab members for all the help and support during my PhD journey, and I am grateful for becoming friends with all of you. Secondly, some thoughts about my PhD life I want to share is, do not give up or get distracted but always stay on what you would like to do. I have had tough times during PhD and before I met Prof. Kuo, but I knew I wanted to pursue this path and career, so I tried everything I could to keep doing research and finish my PhD degree. Life is also hard to predict so even if I just made some choices based on intuition and persistence, the outcome could be better than what I initially expected. Third, I feel that doing research means long-term commit. For a research project, if we work on it long enough, there would always be exciting findings. For the career, academic rewards those who have been in this community long enough. Finally, I would like to wish the best to all the people in our lab in their future study and in life, and for those who are looking to start PhD, I assure you Prof. Kuo and MCL are definitely the best choice you could make!”
Let us wish Harry all the best in his future career!
