Class specific subspace learning for collaborative representation

Bao Di Liu, Bin Shen, Yu Xiong Wang, Weifeng Liu, Yanjiang Wang

Research output: Contribution to journalConference articlepeer-review


Collaborative representation based classification (CRC) has been successfully used for visual recognition and showed impressive performance recently. However, it directly uses the training samples from each class as the subspaces to calculate the minimum residual error for a given testing sample. This leads to high residual error and instability, which is critical especially for a small number of training samples in each class. In this paper, we propose a class specific subspace learning algorithm for collaborative representation. By introducing the dual form of subspace learning, it presents an explicit relationship between the basis vectors and the original image features, and thus enhances the interpretability. Lagrange multipliers are then applied to optimize the corresponding objective function, i.e., learning the weights used in constructing the subspaces. Extensive experimental results demonstrate that the proposed algorithm has achieved superior performance in several visual recognition tasks.

Original languageEnglish (US)
Article number6974364
Pages (from-to)2865-2870
Number of pages6
JournalConference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
Issue numberJanuary
StatePublished - 2014
Externally publishedYes
Event2014 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2014 - San Diego, United States
Duration: Oct 5 2014Oct 8 2014

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Control and Systems Engineering
  • Human-Computer Interaction


Dive into the research topics of 'Class specific subspace learning for collaborative representation'. Together they form a unique fingerprint.

Cite this