Dimensionality-varied deep convolutional neural network for spectral–spatial classification of hyperspectral data

Qu, Haicheng; Liang, Xuejian; Liang, Shichao; Liu, Wanjun

doi:10.1117/1.jrs.12.016007

Cited by 8 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[13][14][15] Supervised methods require a priori knowledge of the ground truth (GT) label information in the learning and assessment stages. 16,17 In the case of semisupervised methods, the knowledge of the number of classes (often given by the GT) and/ or some threshold values, or the number of iterations for iterative methods are required to perform the classification task. 18,19 Finally, unsupervised methods objectively aggregate the objects (pixels) in classes without any knowledge (neither the number of classes to discriminate nor learning samples).…”

Section: Introductionmentioning

confidence: 99%

Learning or assessment of classification algorithms relying on biased ground truth data: what interest?

Chehdi

Cariou

2019

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

The use of ground truth (GT) data in the learning and/or assessment of classification algorithms is essential. Using a biased or simplified GT attached to a remote sensing image to partition does not allow a rigorous explanation of the physical phenomena reflected by such images. Unfortunately, this scientific problem is not always treated carefully and is generally neglected in the relevant literature. Furthermore, the impacts of obtained classification results for decision-making are negative. This is inconsistent when considering investments in both the development of sophisticated sensors and the design of objective classification algorithms. Any GT must be validated according to a rigorous protocol before utilization, which is unfortunately not always the case. The evidence of this problem is provided, using two popular hyperspectral images (Indian Pine and Pavia University) that misleadingly are frequently used without care by the remote sensing community since the associated GTs are not accurate. The heterogeneity of the spectral signatures of some GT classes was proven using a semisupervised and an unsupervised classification method. Through this critical analysis, we propose a general framework for a minimum objective assessment and validation of the GT accuracy, before exploiting them in a classification method. © The Authors. Published by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.

show abstract

Section: Introductionmentioning

confidence: 99%

Learning or assessment of classification algorithms relying on biased ground truth data: what interest?

Chehdi

Cariou

2019

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

show abstract

“…In order to improve the accuracy of HSI classification, numerous methods have been proposed in the past few years. Traditional HSI classification methods which generally focused on spectral bands included k-nearest neighbours, logistic regression, maximum likelihood, etc [2]. Spectral-spatial classification could improve the accuracy of classification prominently [3].…”

Section: Introductionmentioning

confidence: 99%

Parallel Dimensionality-Varied Convolutional Neural Network for Hyperspectral Image Classification

Yin

Liang

et al. 2018

Intelligence Science II

Self Cite

View full text Add to dashboard Cite

Many spectral-spatial classification methods of HSI based on convolutional neural network (CNN) are proposed and achieve outstanding performance recently. However, these methods require tremendous computations with complex network and excessively large model. Moreover, single machine is obviously weak when dealing with big data. In this paper, a parallel dimensionality-varied convolutional neural network (DV-CNN) is proposed to address these issues. The dimensionalities of feature maps extracted vary with stages in DV-CNN, and DV-CNN reduces the dimensionalities of feature maps to simplify the computation and the structure of network without information loss. Besides, the parallel architecture of DV-CNN can obviously reduce the training time. The experiments compared with state-of-the-art methods are performed on Indian Pines and Pavia University scene datasets. The results of experiments demonstrate that parallel DV-CNN can obtain better classification performance, reduce the time consuming and improve the training efficiency.

show abstract

Hyperspectral Image: Fundamentals and Advances

Sowmya¹,

Soman²,

Hassaballah³

2018

Studies in Computational Intelligence

View full text Add to dashboard Cite

Dimensionality-varied deep convolutional neural network for spectral–spatial classification of hyperspectral data

Cited by 8 publications

References 37 publications

Learning or assessment of classification algorithms relying on biased ground truth data: what interest?

Learning or assessment of classification algorithms relying on biased ground truth data: what interest?

Parallel Dimensionality-Varied Convolutional Neural Network for Hyperspectral Image Classification

Hyperspectral Image: Fundamentals and Advances

Contact Info

Product

Resources

About