Unsupervised Detection of Regions of Interest Using Iterative Link Analysis
Gunhee Kim, Antonio B. Torralba · DSpace@MIT (Massachusetts Institute of Technology) · 2009
This paper proposes a fast and scalable alternating optimization technique to de-tect regions of interest (ROIs) in cluttered Web images without labels. The pro-posed approach discovers highly probable regions of object instances by itera-tively 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 state-of-the-art tech-niques and comparable to supervised methods. Also, we test the scalability of our approach with five objects in Flickr dataset consisting of more than 200K images. 1