Parallel Dimensionality-Varied Convolutional Neural Network for Hyperspectral Image Classification - Archive ouverte HAL Access content directly
Conference Papers Year : 2018

Parallel Dimensionality-Varied Convolutional Neural Network for Hyperspectral Image Classification

(1) , (1) , (1) , (1)
1
Haicheng Qu
  • Function : Author
  • PersonId : 1046646
Xiu Yin
  • Function : Author
  • PersonId : 1046647
Xuejian Liang
  • Function : Author
  • PersonId : 1046648
Wanjun Liu
  • Function : Author
  • PersonId : 1046649

Abstract

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.
Fichier principal
Vignette du fichier
474230_1_En_32_Chapter.pdf (245.64 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02118826 , version 1 (03-05-2019)

Licence

Attribution - CC BY 4.0

Identifiers

Cite

Haicheng Qu, Xiu Yin, Xuejian Liang, Wanjun Liu. Parallel Dimensionality-Varied Convolutional Neural Network for Hyperspectral Image Classification. 2nd International Conference on Intelligence Science (ICIS), Nov 2018, Beijing, China. pp.302-309, ⟨10.1007/978-3-030-01313-4_32⟩. ⟨hal-02118826⟩
26 View
14 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More