Joint feature-basis subset selection

Shai Avidan*

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

Abstract

We treat feature selection and basis selection in a unified framework by introducing the masking matrix. If one considers feature selection as finding a binary mask vector that determines which features participate in the learning process, and similarly, basis selection as finding a binary mask vector that determines which basis vectors are needed for the learning process, then the masking matrix is, in particular, the outer product of the feature masking vector and the basis masking vector. This representation allows for a joint estimation of both features and basis. In addition, it allows one to select features that appear in only part of the basis functions. This joint selection of feature/basis subset is not possible when using feature selection and basis selection algorithms independently, thus, the masking matrix help extend feature and basis selection methods while blurring the lines between them. The problem of searching for an optimal masking matrix is NP-hard and we offer a sub-optimal probabilistic method to find it. In particular we demonstrate our ideas on the problem of feature and basis selection for SVM classification and show results for the problem of image classification on faces and vehicles.

Original languageEnglish
Pages (from-to)I283-I290
JournalProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume1
StatePublished - 2004
Externally publishedYes
EventProceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2004 - Washington, DC, United States
Duration: 27 Jun 20042 Jul 2004

Fingerprint

Dive into the research topics of 'Joint feature-basis subset selection'. Together they form a unique fingerprint.

Cite this