National Center for Supercomputing Applications WordPress Master Calendar

View Full Calendar

NCSA staff who would like to submit an item for the calendar can email newsdesk@ncsa.illinois.edu.

Chen Wei "Generalizable Visual Understanding through Inverse Generation"

Event Type
Seminar/Symposium
Sponsor
Illinois Computer Science
Virtual
wifi event
Date
Jan 25, 2024   3:00 pm  
Speaker
Chen Wei, Fifth-year Ph.D Student, Johns Hopkins University
Contact
Candice Steidinger
E-Mail
steidin2@illinois.edu
Views
135
Originating Calendar
Siebel School Speakers Calendar

We look forward to seeing you online on Thursday, January 25. 

Abstract: Generative AI has led to stunning successes in recent years. These models can synthesize realistic and complex visual content conditioned on representations of internal states such as text descriptions, evidently capturing general visual knowledge. Parallel to focusing on enhancing the quality of content generation,  my research concentrates on its inverse: extracting the general visual knowledge from these generative models for generalizable visual understanding. In this talk, I’ll first introduce how a diffusion model as a self-supervised objective enables visual representations adept at both recognition and generation. I’ll then illustrate how unpacking a well-trained text-to-image model leads to image captions with accuracy and comprehensiveness unseen in their uncurated training data. I’ll discuss how the compositional nature of generative models leads to effective extrapolation beyond the training data.

BioChen Wei is a fifth-year Ph.D student at Johns Hopkins University, advised by Professor Alan L. Yuille. Her research focuses on computer vision, with a particular interest in developing generalizable and scalable visual representations. Chen received B.Sc. from Peking University. She has interned at FAIR at Meta and Google DeepMind. 

link for robots only