Dictionary learning for fast classification based on soft-thresholding
From MaRDI portal
Abstract: Classifiers based on sparse representations have recently been shown to provide excellent results in many visual recognition and classification tasks. However, the high cost of computing sparse representations at test time is a major obstacle that limits the applicability of these methods in large-scale problems, or in scenarios where computational power is restricted. We consider in this paper a simple yet efficient alternative to sparse coding for feature extraction. We study a classification scheme that applies the soft-thresholding nonlinear mapping in a dictionary, followed by a linear classifier. A novel supervised dictionary learning algorithm tailored for this low complexity classification architecture is proposed. The dictionary learning problem, which jointly learns the dictionary and linear classifier, is cast as a difference of convex (DC) program and solved efficiently with an iterative DC solver. We conduct experiments on several datasets, and show that our learning algorithm that leverages the structure of the classification problem outperforms generic learning procedures. Our simple classifier based on soft-thresholding also competes with the recent sparse coding classifiers, when the dictionary is learned appropriately. The adopted classification scheme further requires less computational time at the testing stage, compared to other classifiers. The proposed scheme shows the potential of the adequately trained soft-thresholding mapping for classification and paves the way towards the development of very efficient classification methods for vision problems.
Recommendations
- Efficient dictionary learning with sparseness-enforcing projections
- A fast sparse representation based classification
- Supervised dictionary learning with multiple classifier integration
- A max-margin dictionary learning algorithm for sparse representation
- Sparse representation based Fisher discrimination dictionary learning for image classification
Cites work
- A D.C. Optimization Algorithm for Solving the Trust-Region Subproblem
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 6276131 (Why is no real title available?)
- Introduction to global optimization.
- LIBLINEAR: a library for large linear classification
- Online learning for matrix factorization and sparse coding
- Polynomial interior-point algorithms for P_*( ) horizontal linear complementarity problem
- The Concave-Convex Procedure
- The DC (Difference of convex functions) programming and DCA revisited with DC models of real world nonconvex optimization problems
Cited in
(9)- Efficient histogram dictionary learning for text/image modeling and classification
- DC programming and DCA: thirty years of developments
- Efficient dictionary learning with sparseness-enforcing projections
- Neural bag-of-features learning
- Supervised dictionary learning with multiple classifier integration
- Convolutional neural networks analyzed via convolutional sparse coding
- A fast sparse representation based classification
- Compact dictionary pair learning and refining based on principal components analysis
- A DC programming approach for sparse estimation of a covariance matrix
This page was built for publication: Dictionary learning for fast classification based on soft-thresholding
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1799991)
