Deep Learning-Based Classification of Hyperspectral Data

By Yushi Chen, Zhouhan Lin, Xing Zhao, G. Wang, Yanfeng Gu. 2014

2,291 citations recorded by the source corpus.

Subfields: Atmospheric Science, Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

3D Convolutional Neural Networks for Crop Classification with Multi-Temporal Remote Sensing Images (2018, background): “In recent years, studies that were related to convolutional neural network (CNN) has been successfully applied in handwriting recognition from binary images [23], labelling from mainstream RGB image set [24], classification from multi-spectral or hyperspectral data [25], learning from videos [26], c”
Towards better exploiting convolutional neural networks for remote sensing scene classification (2016, background): “Moreover, a myriad of deep learning-based methods appeared exploiting its benefits in the remote sensing community [32, 33, 34, 35].”
A survey: Deep learning for hyperspectral image classification with few labeled samples (2021, methodology): “Classification accuracy obtained by S-DMM [121], 3DCAE [40], SSDL [37], TwoCnn [122], 3DVSCNN [123], SSLstm [75], CNN HSI [28] and SAE LR [34] on PaviaU.”
Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach (2016, neutral): “[24] investigated the stacked”
Stable Prediction across Unknown Environments (2018, background): “From the results, we have following observations and analysis: • The methods LR and DLR can not address the stable prediction problem in all settings.”
Going Deeper With Contextual CNN for Hyperspectral Image Classification (2016, methodology): “[1] used stacked autoencoders (SAE) to learn deep features of hyperspectral signatures in an unsupervised fashion followed by logistic regression used to classify extracted deep features into their appropriate material categories.”
How can Big Data and machine learning benefit environment and water management: a survey of methods, applications, and future directions (2019, methodology): “Chen et al [154] proposed to apply Gabor filtering as an unsupervised pretraining technique before CNN to help extract features, thus indirectly mitigating the CNN overfitting problem caused by the lack of labeled data.”
Deep Learning Based Oil Palm Tree Detection and Counting for High-Resolution Remote Sensing Images (2016, methodology): “In recent years, deep learning based methods have also been applied to hyperspectral image classification [20,21], large-scale land cover classification [22], scene classification [23–25], and object detection [26,27], etc.”
Enhancing the momentum strategy through deep regression (2019, methodology): “(2016) and for classifying hyperspectral data in Chen et al. (2014) all with great successes.”
Spectral–spatial classification of hyperspectral images using deep convolutional neural networks (2015, methodology): “Classification accuracies are compared with previous methods including SVM, discriminant analysis associated with the multilevel logistic (MLL) model (Li, Bioucas-Dias, and Plaza 2012) and stacked autoencoder-logistic regression (SAE-LR) (Chen, Lin, et al. 2014).”
Hyperspectral Image Classification With Deep Feature Fusion Network (2018, methodology): “These compared approaches are divided into two kinds of groups: one is based on the conventional machine learning methods, including the SVM [5], extended morphological profiles (EMPs) [11], EPF [25], and joint sparse representation (JSR) [15]; and the other one is based on DL, including the SAEs [3”
Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines (2018, background): “Analogously to DBNs, SAEs are layerby-layer systems in which the input and hidden layers of the autoencoder work repeatedly.”