Timezone: »

Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos
Gautam Singh · Yi-Fu Wu · Sungjin Ahn

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #125

Unsupervised object-centric learning aims to represent the modular, compositional, and causal structure of a scene as a set of object representations and thereby promises to resolve many critical limitations of traditional single-vector representations such as poor systematic generalization. Although there have been many remarkable advances in recent years, one of the most critical problems in this direction has been that previous methods work only with simple and synthetic scenes but not with complex and naturalistic images or videos. In this paper, we propose STEVE, an unsupervised model for object-centric learning in videos. Our proposed model makes a significant advancement by demonstrating its effectiveness on various complex and naturalistic videos unprecedented in this line of research. Interestingly, this is achieved by neither adding complexity to the model architecture nor introducing a new objective or weak supervision. Rather, it is achieved by a surprisingly simple architecture that uses a transformer-based image decoder conditioned on slots and the learning objective is simply to reconstruct the observation. Our experiment results on various complex and naturalistic videos show significant improvements compared to the previous state-of-the-art.

Author Information

Gautam Singh (Rutgers University)

I am starting my second year as a Ph.D. student at the Department of Computer Science at Rutgers University. My focus area is probabilistic generative models. Prior to this, I worked at IBM Research India for 3 years after finishing my undergrad from IIT Guwahati.

Yi-Fu Wu (Rutgers University)
Sungjin Ahn (KAIST)

More from the Same Authors