4.5 Article

Global and pyramid convolutional neural network with hybrid attention mechanism for hyperspectral image classification

Related references

Note: Only part of the references are listed.
Article Environmental Sciences

Two-Branch Convolutional Neural Network with Polarized Full Attention for Hyperspectral Image Classification

Haimiao Ge et al.

Summary: In this study, a two-branch convolutional neural network with a polarized full attention mechanism is proposed for hyperspectral image classification. The network efficiently extracts spectral and spatial features through two branches and simplifies the kernel sizes of convolutional layers to reduce complexity. The one-shot connection technique improves feature extraction efficiency, and the polarized full attention mechanism fuses feature maps and provides global contextual information. Experimental results validate the effectiveness of the proposed network.

REMOTE SENSING (2023)

Article Computer Science, Artificial Intelligence

Central Attention Network for Hyperspectral Imagery Classification

Huan Liu et al.

Summary: This article analyzes the intrinsic properties of hyperspectral imagery (HSI) and builds two principles for spectral-spatial feature extraction. The proposed SDPCA algorithm and CAN network can extract spectral-spatial information from the central pixel and similar pixels. Experimental results demonstrate the superior classification performance of CAN and MiniCAN compared to other methods.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023)

Article Geochemistry & Geophysics

Hyperspectral Image Classification Based on Kernel-Guided Deformable Convolution and Double-Window Joint Bilateral Filter

Chunhui Zhao et al.

Summary: This research proposes a novel two-stage classification method for hyperspectral image classification based on convolutional neural networks, which can achieve more accurate classification results by extracting spatial-spectral features using deformable convolution and joint bilateral filtering.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2022)

Article Geochemistry & Geophysics

Hyperspectral Image Classification Based on Multiscale SpectralSpatial Deformable Network

Jinyan Nie et al.

Summary: This study proposes an HSI classification method based on multiscale spectral-spatial deformable network, which addresses issues in urban HSI classification by clustering spectra, extracting low-level features, and introducing deformable network. Experimental results demonstrate the superiority of the proposed method over current state-of-the-art methods.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2022)

Article Engineering, Electrical & Electronic

Combining a Crop Growth Model With CNN for Underground Natural Gas Leakage Detection Using Hyperspectral Imagery

Ying Du et al.

Summary: A novel method combining crop growth model and convolutional neural network approach was proposed for nondestructive detection of natural gas microleakage. This method accurately and quickly detects underground natural gas leakage, offering more robustness compared to traditional spectral index-based methods.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2022)

Article Geochemistry & Geophysics

SpectralSpatial Feature Tokenization Transformer for Hyperspectral Image Classification

Le Sun et al.

Summary: In this article, the spectral-spatial feature tokenization transformer (SSFTT) method is proposed to capture spectral-spatial and high-level semantic features. Experimental analysis confirms that this method outperforms other deep learning methods in terms of computation time and classification performance.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Article Computer Science, Artificial Intelligence

Weighted Feature Fusion of Convolutional Neural Network and Graph Attention Network for Hyperspectral Image Classification

Yanni Dong et al.

Summary: In this paper, we propose Weighted Feature Fusion of Convolutional Neural Network and Graph Attention Network (WFCG) for hyperspectral image (HSI) classification. By combining the features of superpixels and pixels, WFCG can fully explore the high-dimensional features and achieve competitive results.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2022)

Article Environmental Sciences

Enhanced TabNet: Attentive Interpretable Tabular Learning for Hyperspectral Image Classification

Chiranjibi Shah et al.

Summary: This paper introduces an interpretable deep tabular data learning architecture called TabNet, which combines tree-based techniques and deep neural networks. Two variations of TabNet, namely TabNets and sTabNet, are proposed to incorporate spatial information. The performance of TabNet-class approaches can be further improved by using unsupervised pretraining.

REMOTE SENSING (2022)

Review Ecology

A systematic review on hyperspectral imaging technology with a machine and deep learning methodology for agricultural applications

Atiya Khan et al.

Summary: With the increasing global population, the issue of organic food becomes severe. Monitoring agricultural activities is challenging, making precision agriculture crucial for decision-making. This study provides a comprehensive review of hyperspectral imaging technology and advanced machine learning algorithms used in agriculture, offering valuable insights for researchers in the field.

ECOLOGICAL INFORMATICS (2022)

Review Agricultural Engineering

Application of hyperspectral imaging systems and artificial intelligence for quality assessment of fruit, vegetables and mushrooms: A review

Jana Wieme et al.

Summary: This paper reviews the application of hyperspectral imaging technology in horticulture and highlights its importance in assessing the quality of fruits, vegetables, and mushrooms. The paper provides an overview of the concept of quality, measurement principles, and the theory and analysis of hyperspectral imaging systems. It also discusses emerging techniques and the use of artificial intelligence in horticulture. Furthermore, the paper addresses challenges and considerations for future research in this field.

BIOSYSTEMS ENGINEERING (2022)

Proceedings Paper Computer Science, Artificial Intelligence

ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and Transformer

Haokui Zhang et al.

Summary: This paper proposes ParC-Net, a pure ConvNet based backbone model that combines the advantages of vision transformers into ConvNets. Experimental results show that ParC-Net outperforms popular lightweight ConvNets and vision transformer-based models in common vision tasks and datasets, while having fewer parameters and faster inference speed.

COMPUTER VISION, ECCV 2022, PT XXVI (2022)

Article Geochemistry & Geophysics

Self-Supervised Divide-and-Conquer Generative Adversarial Network for Classification of Hyperspectral Images

Jie Feng et al.

Summary: This paper proposes a novel self-supervised divide-and-conquer generative adversarial network (SDC-GAN) for hyperspectral image (HSI) classification. The method addresses the issues of mode collapse and limited samples in GAN by leveraging a pretraining cluster task and effective sample division, and improves the classification ability of the discriminator by constructing generic and specific branches.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Article Engineering, Electrical & Electronic

Multiscale Dual-Branch Residual Spectral-Spatial Network With Attention for Hyperspectral Image Classification

Saeed Ghaderizadeh et al.

Summary: The development of remote sensing images has allowed for the identification of materials in inaccessible environments and the study of natural materials on a large scale. This article proposes a multiscale dual-branch residual spectral-spatial network with attention (MDBRSSN) to improve the accuracy of hyperspectral image (HSI) classification, particularly when training samples are limited. The MDBRSSN model achieves high classification accuracy when compared to state-of-the-art methods, as demonstrated in the experiments conducted on four datasets.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2022)

Article Geochemistry & Geophysics

A Band Selection Method With Masked Convolutional Autoencoder for Hyperspectral Image

Yufei Liu et al.

Summary: Band selection (BS) is an effective method to address the issues of spectral redundancy and Hughes phenomenon in hyperspectral images (HSIs). However, existing BS methods lack consideration of the representativeness, redundancy, and information content of selected bands simultaneously, and do not account for the nonlinear relationship between bands. In this letter, a novel unsupervised BS framework called RRI is proposed, which comprehensively considers the band representativeness, redundancy, and information content. The proposed method utilizes a convolutional autoencoder to estimate band representativeness by capturing the inherent nonlinear relationship between bands and leveraging the spatial information of the HSI. Experimental results demonstrate that the RRI method outperforms competitors in terms of classification accuracy and is robust to noisy bands.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2022)

Article Geochemistry & Geophysics

A Deep Multiscale Pyramid Network Enhanced With Spatial-Spectral Residual Attention for Hyperspectral Image Change Detection

Yufei Yang et al.

Summary: Change detection is important in Earth surface observation. This article proposes a deep multiscale pyramid network enhanced with spatial-spectral residual attention for hyperspectral image change detection, which achieves competitive performance.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Article Geochemistry & Geophysics

Multiscanning Strategy-Based Recurrent Neural Network for Hyperspectral Image Classification

Weilian Zhou et al.

Summary: This study proposes a novel multiscanning strategy with recurrent neural networks (RNN) for hyperspectral image (HSI) classification. By considering different scanning orders and concatenating features as input to the RNN, the network can effectively capture the spatial dependence of HSI patches and achieve competitive classification performance on three datasets.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2022)

Article Geochemistry & Geophysics

NAS-Guided Lightweight Multiscale Attention Fusion Network for Hyperspectral Image Classification

Jianing Wang et al.

Summary: This article introduces a lightweight spectral-spatial attention feature fusion network guided by network architecture search, which achieves deeper network structure and higher efficiency in HSI classification.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2021)

Article Environmental Sciences

Spectral and Spatial Global Context Attention for Hyperspectral Image Classification

Zhongwei Li et al.

Summary: In this article, a spectral-spatial network with channel and position global context attention (SSGCA) is proposed to capture discriminative spectral and spatial features. The proposed method utilizes two novel global context attentions to optimize spectral and spatial features for feature enhancement, outperforming other related methods on public HSI datasets.

REMOTE SENSING (2021)

Article Engineering, Electrical & Electronic

Lightweight Tensor Attention-Driven ConvLSTM Neural Network for Hyperspectral Image Classification

Wen-Shuai Hu et al.

Summary: Recurrent neural networks, especially ConvLSTM, have shown promising results in modeling long-term dependencies. A lightweight tensor attention-driven ConvLSTM neural network (TACLNN) is proposed for hyperspectral image classification, outperforming state-of-the-art methods on three widely used benchmarks by enhancing its geometrical structure with a learnable tensor attention residual block module.

IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING (2021)

Article Environmental Sciences

Double-Branch Network with Pyramidal Convolution and Iterative Attention for Hyperspectral Image Classification

Hao Shi et al.

Summary: The study introduces a double-branch network that incorporates a novel pyramidal convolution and an iterative attention mechanism for extracting spectral-spatial features from hyperspectral images. Experimental results demonstrate that the model shows competitive performance in classification.

REMOTE SENSING (2021)

Review Computer Science, Artificial Intelligence

A review on the attention mechanism of deep learning

Zhaoyang Niu et al.

Summary: This paper provides an overview of state-of-the-art attention models and defines a unified model suitable for most attention structures. It describes in detail each step of the attention mechanism implemented in the model and classifies existing attention models based on four criteria. Additionally, it summarizes the use of attention mechanisms in network architectures and typical applications.

NEUROCOMPUTING (2021)

Article Environmental Sciences

A Spectral Spatial Attention Fusion with Deformable Convolutional Residual Network for Hyperspectral Image Classification

Tianyu Zhang et al.

Summary: A new method SSAF-DCR for hyperspectral image classification is proposed to effectively extract spectral-spatial features, and experimental results demonstrate its superiority to some state-of-the-art methods with very few training samples.

REMOTE SENSING (2021)

Article Engineering, Electrical & Electronic

Multiscale Graph Sample and Aggregate Network With Context-Aware Learning for Hyperspectral Image Classification

Yao Ding et al.

Summary: In this article, a multiscale graph sample and aggregate network with a context-aware learning method is proposed for HSI classification. This network can learn global and contextual information of the graph effectively, and solve the impact of original input graph errors on classification. Experimental results show the superiority of the proposed method over state-of-the-art methods.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2021)

Article Geochemistry & Geophysics

Learning to Pay Attention on Spectral Domain: A Spectral Attention Module-Based Convolutional Network for Hyperspectral Image Classification

Lichao Mou et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2020)

Article Engineering, Electrical & Electronic

A Simplified 2D-3D CNN Architecture for Hyperspectral Image Classification Based on Spatial-Spectral Fusion

Chunyan Yu et al.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2020)

Article Geochemistry & Geophysics

Dual-Path Network-Based Hyperspectral Image Classification

Xudong Kang et al.

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS (2019)

Article Geochemistry & Geophysics

Visual Attention-Driven Hyperspectral Image Classification

Juan Mario Haut et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Data-Driven Neuron Allocation for Scale Aggregation Networks

Yi Li et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Article Geochemistry & Geophysics

Spectral-Spatial Unified Networks for Hyperspectral Image Classification

Yonghao Xu et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2018)

Article Geochemistry & Geophysics

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

Zilong Zhong et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2018)

Article Computer Science, Artificial Intelligence

Going Deeper With Contextual CNN for Hyperspectral Image Classification

Hyungtae Lee et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2017)

Article Remote Sensing

Hyperspectral image classification based on morphological profiles and decision fusion

Brajesh Kumar et al.

INTERNATIONAL JOURNAL OF REMOTE SENSING (2017)

Article Geochemistry & Geophysics

Nonlinear Multiple Kernel Learning With Multiple-Structure-Element Extended Morphological Profiles for Hyperspectral Image Classification

Yanfeng Gu et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2016)

Article Engineering, Electrical & Electronic

Deep Convolutional Neural Networks for Hyperspectral Image Classification

Wei Hu et al.

JOURNAL OF SENSORS (2015)

Article Geochemistry & Geophysics

Classification of hyperspectral remote sensing images with support vector machines

F Melgani et al.

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING (2004)