![Institutional Repository [SANDBOX]](images/dias.logo.png "Institutional Repository [SANDBOX]"){kind=logo}
Institutional Repository [SANDBOX]
Technical University of Crete
Technical University of Crete
EN
|
EL
| URI | http://purl.tuc.gr/dl/dias/6CBF8B5D-0DF3-4C71-AA32-133D89222E65 | - |
| Identifier | https://doi.org/10.1109/ICIP.2019.8803268 | - |
| Identifier | https://ieeexplore.ieee.org/document/8803268 | - |
| Language | en | - |
| Extent | 5 pages | en |
| Title | Hyperspectral image classification with tensor-based rank-R learning models | en |
| Creator | Makantasis Konstantinos | en |
| Creator | Μακαντασης Κωνσταντινος | el |
| Creator | Voulodimos, Athanasios | en |
| Creator | Doulamis, Anastasios | en |
| Creator | Doulamis Nikolaos D. | en |
| Creator | Georgoulas Ioannis | en |
| Publisher | Institute of Electrical and Electronics Engineers | en |
| Content Summary | In this paper, we present a general tensor-based nonlinear classifier, the Rank-R Feedforward Neural Network (FNN). In the proposed model, which is an extension of the Rank-1 FNN classifier, the network weights are constrained to satisfy a rank-R Canonical Polyadic Decomposition. By allowing a rank-R, instead of a rank-1, Canonical Polyadic Decomposition of the weights, the learning capacity of the model can be increased, which contributes to avoiding underfitting problems. The effectiveness of the proposed model is scrutinized on a hyperspectral image classification experimental setting, since hyperspectral data can naturally be represented as tensor objects. Performance evaluation results indicate that the proposed model outperforms other state-of-the-art models, including deep learning ones, especially in cases where the number of available training samples is small. | en |
| Type of Item | Πλήρης Δημοσίευση σε Συνέδριο | el |
| Type of Item | Conference Full Paper | en |
| License | http://creativecommons.org/licenses/by/4.0/ | en |
| Date of Item | 2020-04-23 | - |
| Date of Publication | 2019 | - |
| Subject | Hyperspectral image classification | en |
| Subject | Machine learning | en |
| Subject | Tensor rank decomposition | en |
| Bibliographic Citation | K. Makantasis, A. Voulodimos, A. Doulamis, N. Doulamis and I. Georgoulas, "Hyperspectral image classification with tensor-based rank-R learning models," in 26th IEEE International Conference on Image Processing, 2019, pp. 3148-3152. doi: 10.1109/ICIP.2019.8803268 | en |
Copyright © DIAS 2013
