Events Calendar

AI Seminar- Kernel Methods for Unsupervised Domain Adaptation

Speaker: Boqing Gong , University of Central Florida

Talk Title: Kernel Methods for Unsupervised Domain Adaptation

Series: Artificial Intelligence Seminar

Abstract: In many applications (computer vision, natural language processing, speech recognition, etc.), the curse of domain mismatch arises when the test data (of a target domain) and the training data (of some source domain(s)) come from different distributions. Thus, developing techniques for domain adaptation, i.e., generalizing models from the sources to the target, has been a pressing need. In this talk, I will describe our efforts and results on addressing this challenge.

A key observation is that domain adaptation entails discovering and leveraging latent structures in the source and the target domains. To this end, we develop kernel methods. Concretely, our kernel-based adaptation methods exploit various latent structures in the data. In this talk, I will give 3 examples: subspaces for aligning domains, landmarks for bridging the gaps between domains, and clusters by distribution similarity for identifying unknown domains. We demonstrate their effectiveness on well-benchmarked datasets and tasks. This work is conducted with my Ph.D. adviser Dr. Fei Sha and our collaborator Dr. Kristen Grauman.

Biography: Boqing Gong is an Assistant Professor in the Department of Computer Science and the Center for Research in Computer Vision at University of Central Florida. His research lies at the intersection of machine learning and computer vision, and has been focusing on domain adaptation, zero-shot/transfer learning, and visual analytics of objects, attributes, and human activities. Boqing received his Ph.D. in Computer Science from the University of Southern California in 2015, where his work was partially supported by the Viterbi School of Engineering Doctoral Fellowship. He holds a Master of Philosophy degree from the Chinese University of Hong Kong and a Bachelor of Engineering degree from the University of Science and Technology of China.

Host: Linhong Zhu

Webcast: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=26f8433757004b14aaf06c222eda19211d

Location: 11th Flr Conf Rm # 1135, Marina Del Rey

WebCast Link: http://webcasterms1.isi.edu/mediasite/Viewer/?peid=26f8433757004b14aaf06c222eda19211d

Audiences: Everyone Is Invited

Contact: Peter Zamar