Hedging Against Uncertainty via Multiple Diverse Predictions
Dhruv Batra (Virginia Tech)
NICTA SML SEMINARDATE: 2013-11-28
TIME: 11:15:00 - 12:00:00
LOCATION: NICTA - 7 London Circuit
CONTACT: JavaScript must be enabled to display this email address.
ABSTRACT:
Perception problems are hard. Whether it is object detection, pose estimation, or semantic scene understanding, vision systems must deal with tremendous amounts of ambiguity. Unfortunately, idealized probabilistic models for dealing with this uncertainty are typically computationally intractable. This leads to a major formal divide -- we either a) make performance-limiting assumptions and end up with restricted probabilistic models (e.g. "attractive" pairwise MRFs) that don't work too well; or b) abandon the probabilistic framework in favor of rich feed-forward apipelines" (pixels --> regions --> labels) that mismanage uncertainty. In this talk, I will give a high-level overview of some projects in my lab. In one recent project, we have developed a two-stage model where the first stage is a tractable probabilistic model outputs not just a single-best solution, rather a /diverse/ set of plausible solutions. The second stage is a discriminative re-ranker that is free to exploit arbitrarily complex features, and attempts to pick out the best solution from this set. This hybrid model has recently achieved state-of-art performance on Pascal VOC 2012 segmentation dataset. Joint work with: Abner Guzman-Rivera (UIUC), Ankit Laddha (VT), Adarsh Prasad (VT/UT-Austin), Qing Sun (VT), Payman Yadollahpour (TTIC); Stefanie Jegelka (UC Berekely), Pushmeet Kohli (MSRC), Greg Shakhnarovich (TTIC), Danny Tarlow (MSRC).
BIO:
Dhruv Batra is an Assistant Professor at the Bradley Department of Electrical and Computer Engineering at Virginia Tech, where he leads the VT Machine Learning & Perception group. He is a member of the Virginia Center for Autonomous Systems (VaCAS) and the VT Discovery Analytic Center (DAC). Prior to joining VT, he was a Research Assistant Professor at Toyota Technological Institute at Chicago (TTIC), a philanthropically endowed academic computer science institute located in the campus of University of Chicago. He received his M.S. and Ph.D. degrees from Carnegie Mellon University in 2007 and 2010 respectively, advised by Tsuhan Chen. In past, he has held visiting positions at the Machine Learning Department at CMU, CSAIL MIT, Microsoft Research Cambridge and Cornell University. He was a recipient of the Carnegie Mellon Dean's Fellowship in 2007, the Google Faculty Research Award in 2013, and the Virginia Tech Teacher of the Week in 2013. His research interests lie at the intersection of machine learning and computer vision, with a focus on developing efficient probabilistic models that learn from large quantities of data and make progress on difficult perception problems. His research is supported by NSF, Google, and Amazon.
