Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/125528
Title: | Hyperspectral image classification with tensor-based rank-R learning models |
Authors: | Makantasis, Konstantinos Voulodimos, Athanasios Doulamis, Anastasios Doulamis, Nikolaos Georgoulas, Ioannis |
Keywords: | Hyperspectral imaging -- Data processing Spectral imaging -- Data processing Neural networks (Computer science) Calculus of tensors -- Data processing Machine learning |
Issue Date: | 2019-09 |
Publisher: | Institute of Electrical and Electronics Engineers |
Citation: | Makantasis, K., Voulodimos, A., Doulamis, A., Doulamis, N., & Georgoulas, I. (2019, September). Hyperspectral image classification with tensor-based rank-R learning models. IEEE International Conference on Image Processing - ICIP, Taipei. 3148-3152. |
Abstract: | 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. |
URI: | https://www.um.edu.mt/library/oar/handle/123456789/125528 |
Appears in Collections: | Scholarly Works - FacICTAI |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Hyperspectral image classification with tensor based rank R learning models 2019.pdf Restricted Access | 385.9 kB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.