Deep Sparse Representation-based Classification
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2019
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914086110887936 |
|---|---|
| author | Abavisani, Mahdi Patel, Vishal M. |
| author_facet | Abavisani, Mahdi Patel, Vishal M. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1904_11093 |
| institution | arXiv |
| publishDate | 2019 |
| record_format | arxiv |
| spellingShingle | Deep Sparse Representation-based Classification Abavisani, Mahdi Patel, Vishal M. Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 68T45, 62H30 I.5.3; I.2.10 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. |
| title | Deep Sparse Representation-based Classification |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning 68T45, 62H30 I.5.3; I.2.10 |
| url | https://arxiv.org/abs/1904.11093 |