[Colloquium] TTIC Talk: Dhruv Batra, Carnegie Mellon University

[Julia MacGlashan]

When:             *Tuesday, May 25 @ 11:00am
*

Where:           * TTIC Conference Room #526*, 6045 S Kenwood Ave, 5th Floor


Who:              * **Dhruv Batra*, Carnegie Mellon University


Title:          *      **Graph-Structured Discrete Labelling Problems in
Computer Vision: Learning, Inference and Applications*****



 A number of problems in computer vision (e.g., image segmentation, gender
classification of faces, etc) can be formulated as graph-structured discrete
labelling problems, where the goal is to predict labels (e.g.
foreground/background, male/female) for a set of variables (e.g. pixels,
faces in an image, etc) that have some known underlying structure (e.g.,
neighbouring pixels in an image often have related labels). This task of
inferring optimal labels of structured variables is typically posed as the
minimization of a discrete energy function over a graph, and is NP-hard for
general graphs.

In the first part of this talk, I will present algorithms for learning the
parameters of these energy functions from fully-labelled and
partially-labelled training data.

In the second part, we present a new approximate inference algorithm called
Outer-Planar Decomposition (OPD). OPD decomposes the given intractable
energy-minimization problem over a graph into tractable sub-problems over
outerplanar subgraphs and then employs message passing over these subgraphs
to get an approximate global solution for the original graph. OPD
outperforms current state-of-art inference methods on hard synthetic
problems and is competitive on real computer-vision applications.

Finally, in the third part, we demonstrate our work and apply this
structured prediction paradigm to interactive co-segmentation of groups of
related images and interactive 3D reconstruction of objects and scenes.

Bio: Dhruv Batra is a final-year Ph.D. student in the ECE department at
Carnegie Mellon University,  supervised by Tsuhan Chen. For the past 1.5
years, he has been a visiting student at Cornell University. He received a
Masters degree from CMU in 2006, during which he worked with Martial Hebert
from the Robotics Institute. Before joining CMU, he earned a B.Tech from the
Institute of Technology, Benaras Hindu University. His research interests
are computer vision and machine learning; specifically, learning and
inference in Markov Random Fields. He is also interested in applications of
combinatorial optimization algorithms to learning and vision problems.

Host:              Greg Shakhnarovich, greg at ttic.edu
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mailman.cs.uchicago.edu/pipermail/colloquium/attachments/20100519/c3d1d8a5/attachment.htm