Group structured dirty dictionary learning for classification

Dictionary learning techniques have gained tremendous success in many classification problems. Inspired by the dirty model for multi-task regression problems, we proposed a novel method called group-structured dirty dictionary learning (GDDL) that incorporates the group structure (for each task) wit...

Full description

Saved in:
Bibliographic Details
Published in2014 IEEE International Conference on Image Processing (ICIP) pp. 150 - 154
Main Authors Yuanming Suo, Minh Dao, Trac Tran, Mousavi, Hojjat, Srinivas, Umamahesh, Monga, Vishal
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.10.2014
Subjects
Dictionaries
dictionary learning
dirty model
Encoding
Face
Face recognition
Indexes
structured sparsity
Training
Training data
Online AccessGet full text

Cover

More Information
Summary:Dictionary learning techniques have gained tremendous success in many classification problems. Inspired by the dirty model for multi-task regression problems, we proposed a novel method called group-structured dirty dictionary learning (GDDL) that incorporates the group structure (for each task) with the dirty model (across tasks) in the dictionary training process. Its benefits are two-fold: 1) the group structure enforces implicitly the label consistency needed between dictionary atoms and training data for classification; and 2) for each class, the dirty model separates the sparse coefficients into ones with shared support and unique support, with the first set being more discriminative. We use proximal operators and block coordinate decent to solve the optimization problem. GDDL has been shown to give state-of-art result on both synthetic simulation and two face recognition datasets.
ISSN:1522-4880
2381-8549
DOI:10.1109/ICIP.2014.7025029