Learning Visual Categories through a Sparse Representation Classifier based Cross-Category Knowledge Transfer

Ying Lu 1 Liming Chen 1 Alexandre Saidi 1 Zhaoxiang Zhang Yunhong Wang
1 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : To solve the challenging task of learning effective visual categories with limited training samples, we propose a new sparse representation classifier based transfer learning method, namely SparseTL, which propagates the crosscategory knowledge from multiple source categories to the target category. Specifically, we enhance the target classification task in learning a both generative and discriminative sparse representation based classifier using pairs of source categories most positively and most negatively correlated to the target category. We further improve the discriminativeability of the classifier by choosing the most discriminative bins in the feature vector with a feature selection process. The experimental results show that the proposed methodachieves competitive performance on the NUS-WIDE Scene database compared to several state of the art transfer learning algorithms while keeping a very efficient runtime.
Type de document :
Communication dans un congrès
IEEE International Conference on Image Processing 2014, Oct 2014, Paris France. pp.165-169, 2014
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01301117
Contributeur : Équipe Gestionnaire Des Publications Si Liris <>
Soumis le : lundi 11 avril 2016 - 16:30:31
Dernière modification le : mardi 12 avril 2016 - 01:07:10

Identifiants

  • HAL Id : hal-01301117, version 1

Collections

Citation

Ying Lu, Liming Chen, Alexandre Saidi, Zhaoxiang Zhang, Yunhong Wang. Learning Visual Categories through a Sparse Representation Classifier based Cross-Category Knowledge Transfer. IEEE International Conference on Image Processing 2014, Oct 2014, Paris France. pp.165-169, 2014. <hal-01301117>

Partager

Métriques

Consultations de la notice

58