A Full Tensor Network for Hyperspectral Image Classification

doi:10.1109/LGRS.2022.3207301

2022-01-01

PRE

DOI：10.1109/LGRS.2022.3207301

原文链接

原文求助

摘要

En 中文

Hyperspectral image (HSI) is widely used in real-world classification tasks since it contains rich spatial and spectral features consisting of hundreds of continuous bands. However, the rich spectral features always result in dimension disaster for HSI classification. Some traditional methods adopt the strategy of dimensionality reduction in advance to alleviate the influences of high spectral feature dimension, which usually results in degraded classification accuracy due to the hard coupling of the dimensionality reduction model and the classifier. In this letter, we propose a full tensor network (FTN) for HSI classification based on Tucker decomposition-based hidden (TDH) layer and Candecomp/Parafac decomposition-based classification (CPDC) layer. The proposed network can efficiently extract the high-level structural features directly from the original data and classify HSI in a single network without dimension reduction procedure in advance. Moreover, the proposed model has a simple structure and holds fewer parameters than the state-of-the-art classification methods. The experimental results on Pavia University (PU) and Salinas (SA) datasets show that for a training ratio of 5%, the overall accuracy (OA) of our model is averaged 3.41% higher than convolutional neural network (CNN) models while the network parameters are averaged 80.44% less, which validate the merits of the proposed method.

Keyword:

Tensors

Dimensionality reduction

Neurons

Neural networks

Training

Periodic structures

Matrix decomposition

Full tensor network (FTN)

hyperspectral image (HSI) classification

tensor decomposition

期刊

IEEE Geoscience and Remote Sensing Magazine

IF:

16.4

论文数:

1.0W

被引数:

5.1K

机构

Xidian University

学者数:

2.4W

论文数: 1.9W

被引数: 9.7K

引用论文

Octopamine stimulated rise of cAMP in Limulus ventral photoreceptors 章鱼胺刺激鲎腹侧光感受器中cAMP的升高

Vision Research

IF0

1982-01-01

PREAI

U.B. Kaupp; C.C. Malbon; B.-A. Battelle; J.E. Brown

Blockchain Technology Applications in Businesses and Organizations

SSRN Electronic Journal

IF0

2022-01-01

PREAI

Pietro De Giovanni

mTOR-regulated mitochondrial metabolism limits mycobacterium-induced cytotoxicity

Cell

IF0

2022-09-01

OAAI

Antonio J. Pagán; Lauren J. Lee; Joy Edwards-Hicks; Cecilia B. Moens; David M. Tobin; Elisabeth M. Busch-Nentwich; Erika L. Pearce; Lalita Ramakrishnan

Hyperspectral Image Classification Based on 3-D Separable ResNet and Transfer Learning

ieee geoscience and remote sensing magazine

IF4.4

2019-12-01

PREAI

Jiang, Yenan; Li, Ying; Zhang, Haokui

Hyperspectral Image Restoration via Global L1-2 Spatial-Spectral Total Variation Regularized Local Low-Rank Tensor Recovery

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING

IF8.6

2021-04-01

OAAI

Zeng, Haijin; Xie, Xiaozhen; Cui, Haojie; Yin, Hanping; Ning, Jifeng