题目: Improving Person Re-identification with the Generative Adversarial Network

讲者: Dr Liang Zheng

时间: 2017年12月28日  15:00

地点: 学院计算机与控制工程学院 523会议室

Bio: Dr Liang Zheng is a postdoc researcher in the University of Technology Sydney. Prior to joining UTS, he obtained his B.E and PhD degrees from Tsinghua University. He has published over 20 papers in TPAMI, IJCV,  CVPR, ECCV, and ICCV. His works are extensively cited by the community and the most highly cited paper receives 200+ citations within two years of publication. Dr Zheng received the Outstanding PhD Thesis from Chinese Association of Artificial Intelligence, and the Early Career R&D Award from D2D CRC, Australia. His research was featured by the MIT Technical Review and selected into the computer science courses in Stanford University and the University of Texas at Austin.

Abstract: The Generative Adversarial Network (GAN) has made impressive achievement in image generation. Basically, it is composed of a Discriminator and a Generator. The former reveals whether a generated sample is fake or real, while the latter produces samples to cheat the discriminator. While major attention is paid on the visual quality of the generated samples and semi-supervised learning in vivo, we focus on thein vitro application of the generated samples in supervised learning. Particularly, we consider the task of person re-identification (re-ID), a popular vision topic aiming to retrieve images of a queried identity from a large person gallery.