Learning a Deep Similarity Network for Hyperspectral Image Classification

Yang, Bing; Li, Hong; Guo, Ziyang

doi:10.1109/jstars.2020.3041344

Cited by 19 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For effective feature extraction, it is necessary to deal with the subtle interclass difference and large intraclass variations of an HSI [33]. In order to evaluate the feature characterization ability of Prophet on HSIs, the interclass and intraclass variations are calculated and assessed in this section.…”

Section: B Enhancing Features Of Hsi With the Prophet Modelmentioning

confidence: 99%

Multiscale Superpixelwise Prophet Model for Noise-Robust Feature Extraction in Hyperspectral Images

Ren

Sun

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Despite of various approaches proposed to smooth the hyperspectral images (HSIs) before feature extraction, the efficacy is still affected by the noise, even using the corrected dataset with the noisy and water absorption bands discarded. In this study, a novel spectral-spatial feature mining framework, Multiscale Superpixelwise Prophet Model (MSPM), is proposed for noise-robust feature extraction and effective classification of the HSI. The prophet model is highly noise-robust for deeply digging into the complex structured features thus enlarging interclass diversity and improving intraclass similarity. First, the superpixelwise segmentation is produced from the first three principal components of an HSI to group pixels into regions with adaptively determined sizes and shapes. A multiscale prophet model is utilized to extract the multiscale informative trend components from the average spectrum of each superpixel. Taking the multiscale trend signal as the input feature, the HSI data are classified superpixelwisely, which is further refined by a majority vote based decision fusion. Comprehensive experiments on three publicly available datasets have fully validated the efficacy and robustness of our MSPM model when benchmarked with eleven state-of-the-art algorithms, including six spectral-spatial methods and five deep learning ones. Besides, MSPM also shows superiority under limited training samples, due to the combined strategies of superpixelwise fusion and multiscale fusion. Our model has provided a useful solution for noise-robust feature extraction as it achieves superior HSI classification even from the uncorrected dataset without prefiltering the water absorption and noisy bands.

show abstract

Section: B Enhancing Features Of Hsi With the Prophet Modelmentioning

confidence: 99%

Multiscale Superpixelwise Prophet Model for Noise-Robust Feature Extraction in Hyperspectral Images

Ren

Sun

et al. 2023

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Although these traditional shallow models achieve satisfactory performance, due to the large differences in spectral and spatial characteristics between different channels, the ability to effectively characterize the features of ground objects is still limited. with the application and advantages of deep learning network in remote sensing image classification, such as convolutional neural networks (CNNs), recurrent neural networks, RNNs) [6], graph convolutional neural networks (GCNs) [7] and deep belief networks [8]. Researchers have proposed some multi-modality remote sensing data classification methods and used them for RS image classification, improving classification performance and effect.…”

Section: Introductionmentioning

confidence: 99%

A cross fusion network for multi-modality remote sensing classification

wang,

Wang,

2024

Fourth International Conference on Geology, Mapping, and Remote Sensing (ICGMRS 2023)

View full text Add to dashboard Cite

Classification and identification of the materials the earth's surface have long been a fundamental but challenging research topic in geoscience and remote sensing (RS). Although deep learning technology has achieved certain results in remote sensing image classification, it still has certain challenges for multi-modality remote sensing data classification. In this work, we propose a deep learning multi-modality remote sensing image classification network based on pixellevel cross fusion, called DMLCF-Net. In other words, DMLCF-Net provides a unified deep learning multi-modality remote sensing image classification framework, and introduces the strategy of cross fusion to classify multi-modality remote sensing images. The cross-fusion module can obtain compact feature representation from multi-modality remote sensing data, and different modality can exchange information with each other effectively. In addition, to validate the proposed scheme, extensive experiments conducted on multi-modality remote sensing dataset, demonstrate the effectiveness and superiority of the proposed DMLCF-Net in comparison with several state-of-the-art multi-modality remote sensing data classification methods.

show abstract

“…In recent years, some researchers have proposed some traditional multi-channel algorithms, but the classification accuracy and effect are yet to be improved. With the use and advantages of deep learning networks in RS image classification, researchers have proposed various multimodal RS data classification methods, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs) [ 9 ], graph convolutional networks (GCNs) [ 10 ], and deep similarity networks [ 11 ]. These methods have been utilized for RS image classification, surpassing the performance bottleneck of using single channels and achieving better results [ 12 ].…”

Section: Introductionmentioning

confidence: 99%

CMR-net: A cross modality reconstruction network for multi-modality remote sensing classification

Wang,

2024

PLoS ONE

View full text Add to dashboard Cite

In recent years, the classification and identification of surface materials on earth have emerged as fundamental yet challenging research topics in the fields of geoscience and remote sensing (RS). The classification of multi-modality RS data still poses certain challenges, despite the notable advancements achieved by deep learning technology in RS image classification. In this work, a deep learning architecture based on convolutional neural network (CNN) is proposed for the classification of multimodal RS image data. The network structure introduces a cross modality reconstruction (CMR) module in the multi-modality feature fusion stage, called CMR-Net. In other words, CMR-Net is based on CNN network structure. In the feature fusion stage, a plug-and-play module for cross-modal fusion reconstruction is designed to compactly integrate features extracted from multiple modalities of remote sensing data, enabling effective information exchange and feature integration. In addition, to validate the proposed scheme, extensive experiments were conducted on two multi-modality RS datasets, namely the Houston2013 dataset consisting of hyperspectral (HS) and light detection and ranging (LiDAR) data, as well as the Berlin dataset comprising HS and synthetic aperture radar (SAR) data. The results demonstrate the effectiveness and superiority of our proposed CMR-Net compared to several state-of-the-art methods for multi-modality RS data classification.

show abstract

Learning a Deep Similarity Network for Hyperspectral Image Classification

Cited by 19 publications

References 50 publications

Multiscale Superpixelwise Prophet Model for Noise-Robust Feature Extraction in Hyperspectral Images

Multiscale Superpixelwise Prophet Model for Noise-Robust Feature Extraction in Hyperspectral Images

A cross fusion network for multi-modality remote sensing classification

CMR-net: A cross modality reconstruction network for multi-modality remote sensing classification

Contact Info

Product

Resources

About