Tue, Jun 26, 2018 @ 04:00 PM - 06:00 PM
PhD Candidate: Wei-Lun Chao
Title: Transfer Learning for Intelligent Systems in the Wild
Professor Fei Sha (chair)
Professor Laurent Itti
Professor Joseph Lim
Professor Jason Lee (outside member)
Professor Panayiotis Georgiou (outside member)
Date and Time: June 26, 4-6 pm in SAL 322
Developing intelligent systems for vision and language understanding has long been a crucial part that people dream about the future. In the past few years, with the accessibility to large-scale data and the advance of machine learning algorithms, vision and language understanding has had significant progress for constrained environments. However, it remains challenging for unconstrained environments in the wild where the intelligent system needs to tackle unseen objects and unfamiliar language usage that it has not been trained on. Transfer learning, which aims to transfer and adapt the learned knowledge from the training environment to a different but related test environment has thus emerged as a promising paradigm to remedy the difficulty.
My thesis focuses on two challenging paradigms of transfer learning: zero-shot learning and domain adaptation. I will begin with zero-shot learning, which aims to expand the learned knowledge from seen objects, of which we have training data, to unseen objects, of which we have no training data. I will present an algorithm SynC that can construct the classifier of any object class given its semantic description, even without training data, followed by a comprehensive study on how to apply it to different environments. I will then describe an adaptive visual question answering framework that builds upon the insight of zero-shot learning and can further adapt its knowledge to new environments given limited information.
Audiences: Everyone Is Invited
Contact: Lizsl De Leon