Skip to Main content Skip to Navigation
Conference papers

Vector quantizing feature space with a regular lattice

Tinne Tuytelaars 1 Cordelia Schmid 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 : Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a data- independent approach to construct such a visual vocabulary, where the feature space is discretized using a regular lattice. Using hashing techniques, only non-empty bins are stored, and fine-grained grids become possible in spite of the high dimensionality of typical feature spaces. Based on this representation, we can explore the structure of the feature space, and obtain state-of-the-art pixelwise classification results. In the case of image classification, we introduce a class-specific feature selection step, which takes the spatial structure of SIFT-like descriptors into account. Results are reported on the Graz02 dataset.
Document type :
Conference papers
Complete list of metadata

Cited literature [26 references]  Display  Hide  Download
Contributor : THOTH Team Connect in order to contact the contributor
Submitted on : Monday, December 20, 2010 - 10:27:13 AM
Last modification on : Thursday, January 20, 2022 - 5:31:02 PM
Long-term archiving on: : Monday, November 5, 2012 - 2:40:56 PM


Files produced by the author(s)




Tinne Tuytelaars, Cordelia Schmid. Vector quantizing feature space with a regular lattice. ICCV - 11th IEEE International Conference on Computer Vision, Oct 2007, Rio de Janeiro, Brazil. pp.1-8, ⟨10.1109/ICCV.2007.4408924⟩. ⟨inria-00548675⟩



Record views


Files downloads