Hierarchical discriminative sparse coding via bidirectional connections

Zhengping Ji, Wentao Huang, Garrett Kenyon, Luis M.A. Bettencourt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations


Conventional sparse coding learns optimal dictionaries of feature bases to approximate input signals; however, it is not favorable to classify the inputs. Recent research has focused on building discriminative sparse coding models to facilitate the classification tasks. In this paper, we develop a new discriminative sparse coding model via bidirectional flows. Sensory inputs (from bottom-up) and discriminative signals (supervised from top-down) are propagated through a hierarchical network to form sparse representations at each level. The 0-constrained sparse coding model allows highly efficient online learning and does not require iterative steps to reach a fixed point of the sparse representation. The introduction of discriminative top-down information flows helps to group reconstructive features belonging to the same class and thus to benefit the classification tasks. Experiments are conducted on multiple data sets including natural images, hand-written digits and 3-D objects with favorable results. Compared with unsupervised sparse coding via only bottom-up directions, the two-way discriminative approach improves the recognition performance significantly.

Original languageEnglish (US)
Title of host publication2011 International Joint Conference on Neural Networks, IJCNN 2011 - Final Program
Number of pages8
StatePublished - 2011
Externally publishedYes
Event2011 International Joint Conference on Neural Network, IJCNN 2011 - San Jose, CA, United States
Duration: Jul 31 2011Aug 5 2011

Publication series

NameProceedings of the International Joint Conference on Neural Networks


Other2011 International Joint Conference on Neural Network, IJCNN 2011
Country/TerritoryUnited States
CitySan Jose, CA

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence


Dive into the research topics of 'Hierarchical discriminative sparse coding via bidirectional connections'. Together they form a unique fingerprint.

Cite this