Multiple Feature Learning for Hyperspectral Image Classification

By Jun Yu Li, Xin Huang, Paolo Gamba, José M. Bioucas-Dias, Liangpei Zhang, Jon Atli Benediktsson, Antonio J. Plaza. 2015

302 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

HybridSN: Exploring 3-D–2-D CNN Feature Hierarchy for Hyperspectral Image Classification (2019, background): “[6] have applied the learning over the combination of multiple features for the classification of hyperspectral scenes.”
Learning and Transferring Deep Joint Spectral–Spatial Features for Hyperspectral Classification (2017, methodology): “In [13], a multiple feature learning framework was proposed to combine the spectrum, MP features, and nonlinear kernel-based features.”
PCA-Based Edge-Preserving Features for Hyperspectral Image Classification (2017, methodology): “Values of 100, 200, 500, and 1000 are selected as thresholds for the area attributes [49].”
Hyperspectral Image Classification With Deep Learning Models (2018, background): “[28] propose a new multiple feature learning (MFL) framework, which pur-”
Advances in Hyperspectral Image and Signal Processing: A Comprehensive Overview of the State of the Art (2017, background): “In [124], a classification framework was introduced that combines multiple features with the linear and nonlinear class boundaries present in the data without requiring any regularization parameters to control the weights of the considered features (the results are shown as MFL in Table 4).”
Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines (2018, methodology): “Another representative collection of fixed dependency instantiations is related to MP-based methods [6], [13]–[15], [40], [41], which utilized mathematical morphology operators built on preset structural elements to obtain extended morphological MPs (EMAPs) that are used as features for classificati”
Learning multiscale and deep representations for classifying remotely sensed imagery (2016, background): “Recently, multiple feature learning (Li et al., 2015) have been proved to be more effective than CK-based methods as it can exploit the specific physical or acquisition conditions of each feature.”
Novel segmented stacked autoencoder for effective dimensionality reduction and feature extraction in hyperspectral imaging (2016, background): “Finally, in [15], they propose a new classification framework based on the integration of different features, including linear and non-linear ones.”
A deep learning framework for hyperspectral image classification using spatial pyramid pooling (2016, background): “Li et al. (2015) proposed a new framework for multiple feature learning, which can adaptively exploit information from both linear and non-linearly derived features.”
Unsupervised Spectral–Spatial Feature Learning With Stacked Sparse Autoencoder for Hyperspectral Imagery Classification (2015, methodology): “In their recent work [11], they further propose a multiple feature learning (MFL) framework, which can adaptively select the most useful type (linear or nonlinear) of feature for different classes in the scene.”