Deep Sparse Representation-based Classification
This work addresses classification accuracy in computer vision, but it is incremental as it builds on existing SRC methods with deep learning enhancements.
The authors tackled the problem of improving sparse representation-based classification by proposing a transductive deep learning network that integrates a convolutional autoencoder with a fully-connected layer for sparse coding, resulting in better classification results than state-of-the-art SRC methods on three datasets.
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 learn 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. The source code is available at: github.com/mahdiabavisani/DSRC.