Title: Learning to Communicate for few-shot learning

Speaker:  Dr. Lu Liu  ( University of Technology, Sydney )

Time: Wed, Nov.25 2020, PM: 16:00-17:00

Location:  4318, Building No.4, Wushan Campus

Inviter: Prof. Shenquan Liu

Abstract:

      Few-shot learning aims to train a model with only a small number of samples. In single domain few-shot classification problem, a class is underrepresented by few examples. For multi-domain few-shot classification problem, another challenge is how to transform a universal representation for all domains. In this talk, I will introduce how to communicate between classes and domains to improve the representation ability of models for both few-shot learning scenarios.