Improving stacked-autoencoders with 1D convolutional-nets for hyperspectral image land-cover classification

Jijón-Palma, Mario Ernesto; Kern, Jens; Amisse, Caisse; Centeno, Jorge Antônio Silva

doi:10.1117/1.jrs.15.026506

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al [21] proposed a 1D autoencoder network to extract spatial features and spectral features, respectively. Mario et al [22] employed 1D Stacked Autoencoders (SAE) with three layers of encoder and decoder for pixel-based classification. Bai et al [23] proposed a two-stage multi-dimensional convolutional SAE for HRSI classification, which was composed of the SAE-1 sub-model based on 1D Convolutional Neural Network (CNN) and the SAE-2 sub-model based on 2D and 3D convolution operations.…”

Section: Introductionmentioning

confidence: 99%

Lightweight 3D Dense Autoencoder Network for Hyperspectral Remote Sensing Image Classification

Bai,

Sun,

et al. 2023

Sensors

View full text Add to dashboard Cite

The lack of labeled training samples restricts the improvement of Hyperspectral Remote Sensing Image (HRSI) classification accuracy based on deep learning methods. In order to improve the HRSI classification accuracy when there are few training samples, a Lightweight 3D Dense Autoencoder Network (L3DDAN) is proposed. Structurally, the L3DDAN is designed as a stacked autoencoder which consists of an encoder and a decoder. The encoder is a hybrid combination of 3D convolutional operations and 3D dense block for extracting deep features from raw data. The decoder composed of 3D deconvolution operations is designed to reconstruct data. The L3DDAN is trained by unsupervised learning without labeled samples and supervised learning with a small number of labeled samples, successively. The network composed of the fine-tuned encoder and trained classifier is used for classification tasks. The extensive comparative experiments on three benchmark HRSI datasets demonstrate that the proposed framework with fewer trainable parameters can maintain superior performance to the other eight state-of-the-art algorithms when there are only a few training samples. The proposed L3DDAN can be applied to HRSI classification tasks, such as vegetation classification. Future work mainly focuses on training time reduction and applications on more real-world datasets.

show abstract

Section: Introductionmentioning

confidence: 99%

Lightweight 3D Dense Autoencoder Network for Hyperspectral Remote Sensing Image Classification

Bai,

Sun,

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

Two-stage multi-dimensional convolutional stacked autoencoder network model for hyperspectral images classification

Bai

Sun

et al. 2023

Multimed Tools Appl

View full text Add to dashboard Cite

Deep learning models have been widely used in hyperspectral images classification. However, the classification results are not satisfactory when the number of training samples is small. Focused on above-mentioned problem, a novel Two-stage Multi-dimensional Convolutional Stacked Autoencoder (TMC-SAE) model is proposed for hyperspectral images classification. The proposed model is composed of two sub-models SAE-1 and SAE-2. The SAE-1 is a 1D autoencoder with asymmetric structre based on full connection layers and 1D convolution layers to reduce spectral dimensionality. The SAE-2 is a hybrid autoencoder composed of 2D and 3D convolution operations to extract spectral-spatial features from the reduced dimensionality data by SAE-1. The SAE-1 is trained with raw data by unsupervised learning and the encoder of SAE-1 is employed to reduce spectral dimensionality of raw data. The data after dimension reduction is used to train the SAE-2 by unsupervised learning. The fine-tuning of SAE-2 encoder and the training of classifier are implemented simultaneously with small number of samples by supervised learning. Comparative experiments are performed on three widely used hyperspectral remote sensing data. The extensive comparative experiments demonstrate that the proposed architecture can effectively extract deep features and maintain high classification accuracy with small number of training samples.

show abstract

Land use and land cover classification with hyperspectral data: A comprehensive review of methods, challenges and future directions

Moharram

Sundaram

2023

Neurocomputing

View full text Add to dashboard Cite

Improving stacked-autoencoders with 1D convolutional-nets for hyperspectral image land-cover classification

Cited by 4 publications

References 0 publications

Lightweight 3D Dense Autoencoder Network for Hyperspectral Remote Sensing Image Classification

Lightweight 3D Dense Autoencoder Network for Hyperspectral Remote Sensing Image Classification

Two-stage multi-dimensional convolutional stacked autoencoder network model for hyperspectral images classification

Land use and land cover classification with hyperspectral data: A comprehensive review of methods, challenges and future directions

Contact Info

Product

Resources

About