The Robotics Institute

This is a joint project with Antonio Torralba during my visit at MIT and will be presented as a poster at the upcoming NIPS 2009 Conference.

This talk will discuss a fast and scalable alternating optimization technique to detect regions of interest (ROIs) in cluttered Web images without labels. The proposed approach discovers highly probable regions of object instances by iteratively repeating the following two functions: (1) choose the exemplar set (i.e. a small number of highly ranked reference ROIs) across the dataset and (2) refine the ROIs of each image with respect to the exemplar set. These two subproblems are formulated as ranking in two different similarity networks of ROI hypotheses by link analysis. The experiments with the PASCAL 06 dataset show that our unsupervised localization performance is better than one of the state-of-the-art techniques and comparable to supervised methods. Also, we test the scalability of our approach with five objects in a Flickr dataset consisting of more than 200K images.

Gunhee Kim is a Ph.D. student in the Computer Science Department advised by Takeo Kanade at CMU. He received his master's degree under the supervision of Martial Hebert in 2008 from CMU's Robotics Institute. His research interests are computer vision, machine learning, data mining, and biomedical imaging.