BS-Nets: An End-to-End Framework for Band Selection of Hyperspectral Image (2019-04-17T00:00:00.000000Z)

TL;DR

This article proposes a unified BS framework, BS Network (BS-Net), which consists of a band attention module (BAM), which aims to explicitly model the nonlinear interdependences between spectral bands, and a reconstruction network (RecNet) which is used to restore the original HSI from the learned informative bands, resulting in a flexible architecture.

Abstract

Hyperspectral image (HSI) consists of hundreds of continuous narrowbands with high spectral correlation, which would lead to the so-called Hughes phenomenon and the high computational cost in processing. Band selection (BS) has been proven to be effective in avoiding such problems by removing redundant bands. However, many existing BS methods separately estimate the significance for every single band and cannot fully consider the nonlinear and global interaction between spectral bands. In this article, by assuming that a complete HSI band set can be reconstructed from its few informative bands, we propose a unified BS framework, BS Network (BS-Net). The framework consists of a band attention module (BAM), which aims to explicitly model the nonlinear interdependences between spectral bands, and a reconstruction network (RecNet), which is used to restore the original HSI from the learned informative bands, resulting in a flexible architecture. The resulting framework is end-to-end trainable, making it easier to train from scratch and to combine with many existing networks. We implement two versions of BS-Nets, respectively, using fully connected networks (BS-Net-FC) and convolutional neural networks (BS-Net-Conv), and extensively compare their results with popular existing BS approaches on three real hyperspectral data sets, showing that the proposed BS-Nets can accurately select informative band subset with less redundancy and outperform the competitors in terms of classification accuracy with competitive time cost.

Authors

Yaoming Cai

1 papers

Xiaobo Liu

1 papers

Z. Cai

1 papers

TL;DR

Abstract

Authors

References63 items

Finding Multiple Roots of Nonlinear Equation Systems via a Repulsion-Based Adaptive Differential Evolution

$p$ -Laplacian Regularization for Scene Recognition

Deep Multigrained Cascade Forest for Hyperspectral Image Classification

Band Selection of Hyperspectral Images Using Multiobjective Optimization-Based Sparse Self-Representation

Laplacian-Regularized Low-Rank Subspace Clustering for Hyperspectral Image Band Selection

A Correlation-Based Feature Weighting Filter for Naive Bayes

Laplacian Regularized Spatial-Aware Collaborative Graph for Discriminant Analysis of Hyperspectral Imagery

Hierarchical ensemble of Extreme Learning Machine

Dual Attention Network for Scene Segmentation

Hyperspectral band selection based on multi-objective optimization with high information and low redundancy

A multi-objective approach to welding shop scheduling for makespan, noise pollution and energy consumption

CBAM: Convolutional Block Attention Module

Hypergraph $p$ -Laplacian Regularization for Remotely Sensed Image Recognition

Optimal Clustering Framework for Hyperspectral Band Selection

A Geometry-Based Band Selection Approach for Hyperspectral Image Analysis

Spectral–Spatial Residual Network for Hyperspectral Image Classification: A 3-D Deep Learning Framework

Graph-Regularized Fast and Robust Principal Component Analysis for Hyperspectral Band Selection

Band-Specified Virtual Dimensionality for Band Selection: An Orthogonal Subspace Projection Approach

A mixed-scale dense convolutional neural network for image analysis

Non-local Neural Networks

Generative Adversarial Networks: An Overview

Unsupervised hyperspectral band selection via multi-feature information-maximization clustering

High spatial resolution spectral unmixing for mapping ash species across a complex urban environment

Squeeze-and-Excitation Networks

Fast and Robust Self-Representation Method for Hyperspectral Band Selection

Supervised Gaussian Process Latent Variable Model for Hyperspectral Image Classification

Instance cloned extreme learning machine

Deep Fully Convolutional Network-Based Spatial Distribution Prediction for Hyperspectral Image Classification

Attention is All you Need

Cascaded Recurrent Neural Networks for Hyperspectral Image Classification

Residual Attention Network for Image Classification

Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification

SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning

Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks

Deep Learning for Remote Sensing Data: A Technical Tutorial on the State of the Art

Deep feature weighting for naive Bayes and its application to text classification

Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach

Dual-Clustering-Based Hyperspectral Band Selection by Contextual Analysis

Recent advances in convolutional neural networks

Effective Approaches to Attention-based Neural Machine Translation

Spatial Transformer Networks

Mutual-Information-Based Semi-Supervised Hyperspectral Band Selection With High Discrimination, High Information, and Low Redundancy

Band Selection Using Improved Sparse Subspace Clustering for Hyperspectral Imagery Classification

Generation of Spectral–Temporal Response Surfaces by Combining Multispectral Satellite and Hyperspectral UAV Imagery for Precision Agriculture Applications

Deep learning and the information bottleneck principle

Show, Attend and Tell: Neural Image Caption Generation with Visual Attention

A New Sparsity-Based Band Selection Method for Target Detection of Hyperspectral Image

Hyperspectral Band Selection by Multitask Sparsity Pursuit

A Fast Volume-Gradient-Based Band Selection Method for Hyperspectral Image

Click Prediction for Web Image Reranking Using Multimodal Sparse Coding

Parameter extraction of solar cell models using repaired adaptive differential evolution

Hyperspectral imaging for non-contact analysis of forensic traces.

Clustering-based hyperspectral band selection using sparse nonnegative matrix factorization

Classification of hyperspectral remote sensing images with support vector machines

Estimation of number of spectrally distinct signal sources in hyperspectral imagery

A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification

A Problem of Dimensionality: A Simple Example

Pollution source positioning in a water supply network based on expensive optimization

GENERATIVE ADVERSARIAL NETS

Deep Recurrent Neural Networks for Hyperspectral Image Classification

Unsupervised Band Selection Based on Evolutionary Multiobjective Optimization for Hyperspectral Images

Deep Learning

Medical hyperspectral imaging: a review

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names