International Journal of Computer Vision

, Volume 85, Issue 2, pp 143–166

Foreground Focus: Unsupervised Learning from Partially Matching Images

Article

DOI: 10.1007/s11263-009-0252-y

Cite this article as:
Lee, Y.J. & Grauman, K. Int J Comput Vis (2009) 85: 143. doi:10.1007/s11263-009-0252-y

Abstract

We present a method to automatically discover meaningful features in unlabeled image collections. Each image is decomposed into semi-local features that describe neighborhood appearance and geometry. The goal is to determine for each image which of these parts are most relevant, given the image content in the remainder of the collection. Our method first computes an initial image-level grouping based on feature correspondences, and then iteratively refines cluster assignments based on the evolving intra-cluster pattern of local matches. As a result, the significance attributed to each feature influences an image’s cluster membership, while related images in a cluster affect the estimated significance of their features. We show that this mutual reinforcement of object-level and feature-level similarity improves unsupervised image clustering, and apply the technique to automatically discover categories and foreground regions in images from benchmark datasets.

Keywords

Object recognition Feature selection Unsupervised learning Feature descriptor 

Copyright information

© Springer Science+Business Media, LLC 2009

Authors and Affiliations

  1. 1.Department of Electrical and Computer EngineeringUniversity of Texas at AustinAustinUSA
  2. 2.Department of Computer SciencesUniversity of Texas at AustinAustinUSA

Personalised recommendations