CSAIL Event Calendar: Previous Series

Learning a Compact Image Code for Efficient Recognition of Novel Classes

Speaker: Lorenzo Torresani , Visual Learning Group, Dartmouth College
Date: April 4 2012
Time: 12:30PM to 1:30PM
Location: Star Seminar Room (D463)
Host: Lorenzo Rosasco, IIT@MIT, CBCL, BCS Dept.

In this talk I will discuss methods enabling efficient object-class recognition in large image collections. We are specifically interested in scenarios where the classes to be recognized are not known in advance. The motivating application is "object-class search by example" where a user provides at query time a small set of training images defining an arbitrary novel category and the system must retrieve images belonging to this class from a large database. This application scenario poses challenging requirements on the system design: the object classifier must be learned efficiently at query time from few examples; recognition must have low computational cost with respect to the database size; finally, compact image descriptors must be used to allow storage of large collections in memory.

We propose to address these requirements by learning a compact image code optimized to yield good categorization accuracy with linear (i.e., efficient) classifiers: even when the representation is compressed to less than 300 bytes per image, linear classifiers trained on our descriptor yield accuracy matching the state-of-the-art but at orders of magnitude lower computational cost.

See other events that are part of Brains and Machines Seminar Series 2011/2012

See other events happening in April 2012