log in  |  register  |  feedback?  |  help  |  web accessibility
PhD Defense: Practical Robust Learning under Domain Shifts
Luyu Yang
Wednesday, July 13, 2022, 10:30 am-12:30 pm Calendar
  • You are subscribed to this talk through .
  • You are watching this talk through .
  • You are subscribed to this talk. (unsubscribe, watch)
  • You are watching this talk. (unwatch, subscribe)
  • You are not subscribed to this talk. (watch, subscribe)
The data we create is shifting rapidly. Despite the domain shifts among the images, we as humans still recognize the image. However, these shifts are a much bigger challenge for machines. The fundamental question is: how can we make machines as adaptive as humans? During my PhD, I have worked towards addressing this question through advances in the study of robust learning under domain shifts via domain adaptation.

To enable real systems with demonstrated robustness, the study of domain adaptation needs to move from ideals to realities. In current domain adaptation research, these ideals fall into two categories: i) The trained model can generate invariant representations that work well on both the source and target domains. ii) The domain shift from the source to the target domain can be accurately modeled and then adapted. These ideals are generally not consistent with reality. First, in real scenarios, all resources are under a fixed budget. The model size cannot expand infinitely to handle the complexity of multiple domains. Second, there will not be datasets perfectly sliced into each domain annotated for alignment. Third, the domain shift often changes with time and therefore cannot be modeled only once. These real-world challenges are more than simple restrictions on the existing methods, and call for entirely new designs. In my dissertation research I propose to address these limitations from three aspects: First, domain adaptation should be time-sensitive; Second, true domain labels are hard to obtain; Finally, we need a new perspective to understand the robustness of domain adaptation.

Examining Committee:
Dean's Representative:
Dr. Abhinav Shrivastava    
Dr. Larry S. Davis 

Dr. Joseph JaJa 
Dr. Ramani Duraiswami  
Judy Hoffman (Georgia Tech)

Luyu Yang is a PhD student advised by Prof. Abhinav Shrivastava and Prof. Larry S. Davis. Her research focuses on the intersection of computer vision and machine learning. During her PhD study, she develops learning algorithms which facilitate the transfer of information through unsupervised and semi-supervised model adaptation, through which her work enables systems to tackle real-world variations and minimizes human supervision. Before this, she has also worked on activity recognition in videos.

This talk is organized by Tom Hurst