CS Events

Computer Science Department Colloquium

Unsupervising Vision via Object-Centric World Models


Download as iCal file

Tuesday, December 08, 2020, 10:30am


Speaker: Dr. Sungjin Ahn


Sungjin Ahn is an Assistant Professor of Computer Science at Rutgers University and directs the Rutgers Machine Learning (RUML) lab. He is also affiliated with Rutgers Center for Cognitive Science. He is interested in and have expertise in developing methods for probabilistic learning, deep learning, and their intersection. He is also particularly interested in developing an AI-agent that can discover underlying structure and representations of the world in an unsupervised manner and through interactions with the environment. He received Ph.D. at the University of California, Irvine with Max Welling and did a postdoc with Yoshua Bengio at Mila. Then, he joined Rutgers University in Fall 2018. He has co-organized ICML 2020 Workshop on Object-Oriented Learning and received the ICML best paper award in ICML 2012.

Location : Via Webex recording

Event Type: Computer Science Department Colloquium

Abstract: Objects and their interactions are the foundational structure of the world that plays the central role in our perception, reasoning, and control of the world. Incorporating such structural knowledge is thus expected to resolve various limitations of current deep learning systems in reasoning, causality, modularity, and systematic generalization. However, current deep learning systems are limited in providing such structures: they either extensively rely on human annotations or uses unsupervised representations with a minimal uninterpretable structure. In this talk, I present recent advances in object-centric latent variable models. I first argue that this class of models provide a probabilistic modeling framework to learn interpretable, structured, and adaptable representations as well as the compositional imagination of multi-object scenes in an unsupervised manner. Also, I present the benefits of combining symbolic and distributed representations in these models, and an approach to learn three-dimensional scene representations in an object-centric manner. I conclude that human-like AI agents should understand the causal structured of the world and the object-centric representations can be the foundation of building such world models.

Contact  Host: Dr. Matthew Stone

Recording Link: https://rutgers.webex.com/rutgers/ldr.php?RCID=ac1be1310c8741c7a0c9cae949fd2a1a
Pass: Sungjin1