中央研究院 資訊科學研究所

活動訊息

友善列印

列印可使用瀏覽器提供的(Ctrl+P)功能

CITI--2020資通產業講座:Domain Adaptation and Generalization using Shallow and Deep Representations

:::

CITI--2020資通產業講座:Domain Adaptation and Generalization using Shallow and Deep Representations

  • 講者Rama Chellappa 教授 (University of Maryland)
    邀請人:陳駿丞
  • 時間2019-09-17 (Tue.) 10:30 ~ 12:00
  • 地點資創中心122演講廳
摘要

Domain adaptation techniques refer to a class of methods that attempt to bridge the differences between the distributions of training and test data. This classical problem in pattern recognition and machine learning has generated renewed interest due to the multitudes of ways in which data is collected. First, we review recent methods developed for unsupervised domain adaptation using Grassmannian representations. Next, we present methods for unsupervised domain adaptation using sparse representations such as dictionaries. Finally, we present an approach that leverages unsupervised data to bring the source and target distributions closer in a learned joint feature space. This is accomplished by inducing a symbiotic relationship between the learned embedding and a generative adversarial network. We demonstrate the impact of these methods for object and face recognition as well as semantic segmentation problems.

 

BIO

Prof. Rama Chellappa is a Distinguished University Professor, a Minta Martin Professor of Engineering and a Professor in the ECE department and the Institute for Advanced Computer Studies at University of Maryland.  His current research interests span many areas in image processing, computer vision, machine learning and pattern recognition. Prof. Chellappa has received several awards from IEEE, the International Association of Pattern Recognition, the University of Southern California and the University of Maryland. He was recognized as an Outstanding Electrical and Computer Engineer by Purdue University and received the Distinguished Alumni Award from the Indian Institute of Science. He served as the Editor-in-Chief of PAMI, as a Distinguished Lecturer of the IEEE Signal Processing Society and as the President of IEEE Biometrics Council. He is a Golden Core Member of the IEEE Computer Society; He is a Fellow of IEEE, IAPR, OSA, AAAS, ACM and AAAI and holds six patents.