Skip to Main content Skip to Navigation
Conference papers

Learning Visual Similarity Measures for Comparing Never Seen Objects

Eric Nowak 1 Frédéric Jurie 2
2 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, Grenoble INP - Institut polytechnique de Grenoble - Grenoble Institute of Technology
Abstract : In this paper we propose and evaluate an algorithm that learns a similarity measure for comparing never seen objects. The measure is learned from pairs of training images labeled "same" or "different". This is far less informative than the commonly used individual image labels (e.g. "car model X"), but it is cheaper to obtain. The proposed algorithm learns the characteristic differences between local descriptors sampled from pairs of "same" and "different" images. These differences are vector quantized by an ensemble of extremely randomized binary trees, and the similarity measure is computed from the quantized differences. The extremely randomized trees are fast to learn, robust due to the redundant information they carry and they have been proved to be very good clusterers. Furthermore, the trees efciently combine different feature types (SIFT and geometry). We evaluate our innovative similarity measure on four very different datasets and consistantly outperform the state-of-the-art competitive approaches.
Complete list of metadata
Contributor : Hal System Connect in order to contact the contributor
Submitted on : Monday, January 14, 2008 - 4:08:36 PM
Last modification on : Tuesday, October 19, 2021 - 11:13:06 PM
Long-term archiving on: : Tuesday, April 13, 2010 - 5:03:39 PM


Publisher files allowed on an open archive




Eric Nowak, Frédéric Jurie. Learning Visual Similarity Measures for Comparing Never Seen Objects. CPVR 2007 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2007, Minneapolis, United States. pp.1-8, ⟨10.1109/CVPR.2007.382969⟩. ⟨hal-00203958⟩



Les métriques sont temporairement indisponibles