Learning from Limited Supervision: Models and Optimization

Recently, learning from limited supervision has drawn tremendous research interests within the machine learning and computer vision communities. The purpose is to mitigate the lack of full and laborious annotations in a breadth of important application areas. In this talk, I will discuss some recent developments in this direction, highlighting and connecting various popular settings of learning from limited supervision: Few-shot learning, semi/weakly supervised learning and unsupervised domain adaptation. 

I will focus on how to tackle these problems by enforcing various types of regularizers, priors and constraints on training deep neural networks, which can leverage unlabeled data and embed domain-specific knowledge. I will discuss several key technical aspects in the context of learning with limited labels, including constrained optimization, Laplacian/Conditional Random Fields (CRFs) regularization and Shannon-Entropy/Mutual-Information losses. 

I will emphasize how more attention should be paid to optimization methods, going beyond standard gradient descent. The talk includes various experimental illustrations and applications. 

Class Timetable

  Start Time End Time Professor

Class Information

 Open: July 4, 2022

Class Trainer