Deep Sparse Representation-Based Classification
- 24 April 2019
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 26 (6) , 948-952
Abstract
We present a transductive deep learning-based formulation for the sparse representation-based classification (SRC) method. The proposed network consists of a convolutional autoencoder along with a fully-connected layer. The role of the autoencoder network is to lean robust deep features for classification. On the other hand, the fully-connected layer, which is placed in between the encoder and the decoder networks, is responsible for finding the sparse representation. The estimated sparse codes are then used for classification. Various experiments on three different datasets show that the proposed network leads to sparse representations that give better classification results than state-of-the-art SRC methods.Keywords
All Related Versions
Funding Information
- National Science Foundation (1618677)
- US Office of Naval Research (N00014-16-1-3134)
This publication has 31 references indexed in Scilit:
- Latent Space Sparse and Low-Rank Subspace ClusteringIEEE Journal of Selected Topics in Signal Processing, 2015
- Multiple Kernel Learning for Sparse Representation-Based ClassificationIEEE Transactions on Image Processing, 2014
- Joint Sparse Representation for Robust Multimodal Biometrics RecognitionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Sparse Subspace Clustering: Algorithm, Theory, and ApplicationsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Kernel sparse representation based classificationNeurocomputing, 2012
- Kernel Sparse Representation for Image Classification and Face Recognition2010
- $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse RepresentationIEEE Transactions on Signal Processing, 2006
- For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solutionCommunications on Pure and Applied Mathematics, 2006
- Decoding by Linear ProgrammingIEEE Transactions on Information Theory, 2005
- A database for handwritten text recognition researchIEEE Transactions on Pattern Analysis and Machine Intelligence, 1994