Visual Inference by Data Driven Markov Chain Monte Carlo

Song-Chun Zhu


In this talk, I will present a computing paradigm called DDMCMC for visual inference. The objective of the paradigm is to provide an integrated solution to conventional tasks: image segmentation, curve grouping and recognition in a common framework. The basic idea is to utilize discriminative model computed in a "bottom-up" process as proposal probabilities to activate generative models in a "top-down" process and thus drive the Markov chain for fast convergences. The Markov chain consists of a number of reversible jumps to search in a complex state space which contains many subspaces of varying dimensions. I will discuss various theoretical results on the MCMC hitting-time/mixing-time. One particular new technique is the Swendsen-Wang Cut (SWC) that we developed recently. It can generate fair samples on the graph partition spaces with fast mixing speed. This paradigm is also applied to motion segmentation and 3D reconstruction from a single image. I will show a number of experiments in the talk.

This is joint work with three graduate students: Z.W. Tu, F. Han, and A. Barbu, and a colleague A.L. Yuille.


Song-Chun Zhu received his Ph.D from Horvard in 1996 (with Dr. Mumford) and currently he is an associate professor at UCLA, jointly at Statistics and Computer Science. His research is focused on statistical modeling and learning of visual patterns and shatistical computing for visual inference.

Maintained by Philippos Mordohai