My name is Yanwu Xu, currently a 1st-year PhD student in Intellegent System at University of Pittsburgh, advised by Dr. Kayhan Batmanghelich and co-advised by Dr. Mingming Gong. My current research interests are Generative Adversarial Learning and Domain Transfer. Before that, I obtained B.S. degree in Electrical Mechanical Engineering department at Central South University in 2017.
Congrats to our Conditional GAN paper accepted by NeuralIPS 2019 (Spotlight 2.4%)!. In this work, Dr. Mingming Gong and me have the equal contribution to this work which solve a critical problem in AC-GAN. below is the general idea of our work.
Conditional generative models enjoy remarkable progress over the past few years. One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN), which generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier. However, the diversity of the generated samples by AC-GAN tends to decrease as the number of classes increases, hence limiting its power on large-scale data. In this paper, we identify the source of the low diversity issue theoretically and propose a practical solution to solve the problem. We show that the auxiliary classifier in AC-GAN imposes perfect separability, which is disadvantageous when the supports of the class distributions have significant overlap. To address the issue, we propose Twin Auxiliary Classifiers Generative Adversarial Net (TAC-GAN) that further benefits from a new player that interacts with other players (the generator and the discriminator) in GAN. Theoretically, we demonstrate that TAC-GAN can effectively minimize the divergence between the generated and real-data distributions. Extensive experimental results show that our TAC-GAN can successfully replicate the true data distributions on simulated data, and significantly improves the diversity of class-conditional image generation on real datasets.
One paper is accepted by NeurIPS 2019.
One paper is accepted by BraTS Challenge 2018.
One paper is accepted by ACCV 2018.