Skip to Main content Skip to Navigation
New interface
Conference papers

Learning visual distance function for object identification from one example

Eric Nowak 1 Frédéric Jurie 2, * 
* Corresponding author
2 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Laboratoire d'informatique GRAphique, VIsion et Robotique de Grenoble, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : Comparing images is essential to several computer vision problems, like image retrieval or object identification. The comparison of two images heavily relies on the definition of a good distance function. Standard functions (e.g. the euclidean distance in the original feature space) are too generic and fail to encode the domain specific information. In this paper, we propose to learn a similarity measure specific to a given category (e.g. cars). This distance is learned from a training set of pairs of images labeled “same” or “different”, indicating if the two images represent the same object (e.g. same car model) or not. After learning, this measure is used to predict how similar two images of never seen objects are (see figure 1).
Document type :
Conference papers
Complete list of metadata

Cited literature [9 references]  Display  Hide  Download
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Thursday, January 6, 2011 - 8:47:33 AM
Last modification on : Wednesday, February 2, 2022 - 3:58:14 PM
Long-term archiving on: : Thursday, April 7, 2011 - 2:30:03 AM


Files produced by the author(s)


  • HAL Id : inria-00548582, version 1



Eric Nowak, Frédéric Jurie. Learning visual distance function for object identification from one example. Learning to Compare Examples (NIPS'06 Workshop), Dec 2006, Whistler, Canada. ⟨inria-00548582⟩



Record views


Files downloads