Task-Driven Dictionary Learning

Modeling data with linear combinations of a few elements from a learned dictionary has been the focus of much recent research in machine learning, neuroscience, and signal processing. For signals such as natural images that admit such sparse representations, it is now well established that these mod...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on pattern analysis and machine intelligence Vol. 34; no. 4; pp. 791 - 804
Main Authors:	Mairal, J., Bach, F., Ponce, J.
Format:	Journal Article
Language:	English
Published:	Los Alamitos, CA IEEE 01.04.2012 IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Institute of Electrical and Electronics Engineers
Subjects:	Algorithms Applied sciences Artificial intelligence Basis pursuit Classification compressed sensing Computer science; control theory; systems Cost function Data processing. List processing. Character string processing Databases, Factual Detection, estimation, filtering, equalization, prediction Dictionaries dictionary learning Exact sciences and technology Humans Information systems. Data bases Information, signal and communications theory Lasso Machine Learning matrix factorization Memory organisation. Data processing Pattern Recognition, Automated - methods Pattern recognition. Digital image processing. Computational geometry semi-supervised learning Sensors Signal and communications theory Signal, noise Software Sparse matrices Statistics Studies Telecommunications and information theory Vectors Dictionaries compressed sensing Scalability Image processing Lasso Matrix factorization dictionary learning Modeling Optimization Restoration Semi-supervised learning Natural scenes Sparse representation Mathematical programming Nonlinear problems Regression analysis Basis pursuit Supervised classification Inverse problem Supervised learning Signal processing Data models Large scale Manuscript character Artificial intelligence Image classification matrix factorization semi-supervised learning sparse principal component analysis sparse coding
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Modeling data with linear combinations of a few elements from a learned dictionary has been the focus of much recent research in machine learning, neuroscience, and signal processing. For signals such as natural images that admit such sparse representations, it is now well established that these models are well suited to restoration tasks. In this context, learning the dictionary amounts to solving a large-scale matrix factorization problem, which can be done efficiently with classical optimization tools. The same approach has also been used for learning features from data for other purposes, e.g., image classification, but tuning the dictionary in a supervised way for these tasks has proven to be more difficult. In this paper, we present a general formulation for supervised dictionary learning adapted to a wide variety of tasks, and present an efficient algorithm for solving the corresponding optimization problem. Experiments on handwritten digit classification, digital art identification, nonlinear inverse image problems, and compressed sensing demonstrate that our approach is effective in large-scale settings, and is well suited to supervised and semi-supervised classification, as well as regression tasks for data that admit sparse representations.
Bibliography:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ISSN:	0162-8828 1939-3539 2160-9292 1939-3539
DOI:	10.1109/TPAMI.2011.156