Title
Stable Discriminative Dictionary Learning Via Discriminative Deviation
Abstract
Discriminative learning of sparse-code based dictionaries tends to be inherently unstable. We show that using a discriminative version of the deviation function to learn such dictionaries leads to a more stable formulation that can handle the reconstruction/discrimination trade-off in a principled manner. Results on Graz02 and UCF Sports datasets validate the proposed formulation. © 2012 ICPR Org Committee.
Publication Date
12-1-2012
Publication Title
Proceedings - International Conference on Pattern Recognition
Number of Pages
3224-3227
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
Copyright Status
Unknown
Socpus ID
84874564098 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/84874564098
STARS Citation
Khan, Nazar and Tappen, Marshall, "Stable Discriminative Dictionary Learning Via Discriminative Deviation" (2012). Scopus Export 2010-2014. 3897.
https://stars.library.ucf.edu/scopus2010/3897