What You Saw Is Not What You Get: domain adaptation for deep learning

Domain adaptation transfers knowledge from offline training domains to new test domains. Traditional supervised learning suffers from poor generalization when the test data distribution differs from training. This problem arises in many practical applications, including perception for autonomous vehicles. For example, if the perception model is trained on a dataset collected in specific weather conditions and/or geographical locations, its performance is likely to drop significantly in novel test conditions and locations. This is true even for deep neural models that are trained on large scale datasets. I will discuss our recent work focusing on domain adaptation in unsupervised scenarios, where the target domain is assumed to have no annotated labels. Specifically, I will describe a generalized framework based on end-to-end unsupervised domain alignment using domain-adaptive losses, such as the adversarial, maximum mean discrepancy, and correlation alignment losses. This work is in collaboration with the vision group at UC Berkeley.
Prof. Kate Saenko is an Assistant Professor at the Computer Science Department at Boston University, and the director of the Computer Vision and Learning Group and member of the IVC group. She received her PhD from MIT. Previously, she was an Assistant Professor at the UMass Lowell CS department, Postdoctoral Researcher at the International Computer Science Institute, a Visiting Scholar at UC Berkeley EECS and a Visiting Postdoctoral Fellow in the School of Engineering and Applied Science at Harvard University. Her research interests are in developing machine learning for image and language understanding, multimodal perception for autonomous systems, and adaptive intelligent human-computer interfaces.