Manifold-learning-based feature extraction for classification of hyperspectral data: A review of advances in manifold learning
Advances in hyperspectral sensing provide new capability for characterizing spectral
signatures in a wide range of physical and biological systems, while inspiring new methods …
signatures in a wide range of physical and biological systems, while inspiring new methods …
Multimodal hyperspectral remote sensing: An overview and perspective
Y Gu, T Liu, G Gao, G Ren, Y Ma, J Chanussot… - Science China …, 2021 - Springer
Since the advent of hyperspectral remote sensing in the 1980s, it has made important
achievements in aerospace and aviation field and been applied in many fields …
achievements in aerospace and aviation field and been applied in many fields …
Manifold regularized sparse NMF for hyperspectral unmixing
Hyperspectral unmixing is one of the most important techniques in analyzing hyperspectral
images, which decomposes a mixed pixel into a collection of constituent materials weighted …
images, which decomposes a mixed pixel into a collection of constituent materials weighted …
Tensor discriminative locality alignment for hyperspectral image spectral–spatial feature extraction
In this paper, we propose a method for the dimensionality reduction (DR) of spectral-spatial
features in hyperspectral images (HSIs), under the umbrella of multilinear algebra, ie, the …
features in hyperspectral images (HSIs), under the umbrella of multilinear algebra, ie, the …
Non-linear spectral unmixing by geodesic simplex volume maximization
R Heylen, D Burazerovic… - IEEE Journal of Selected …, 2010 - ieeexplore.ieee.org
Spectral mixtures observed in hyperspectral imagery often display nonlinear mixing effects.
Since most traditional unmixing techniques are based upon the linear mixing model, they …
Since most traditional unmixing techniques are based upon the linear mixing model, they …
Learning a robust local manifold representation for hyperspectral dimensionality reduction
Local manifold learning has been successfully applied to hyperspectral dimensionality
reduction in order to embed nonlinear and nonconvex manifolds in the data. Local manifold …
reduction in order to embed nonlinear and nonconvex manifolds in the data. Local manifold …
[HTML][HTML] Diffusion nets
Non-linear manifold learning enables high-dimensional data analysis, but requires out-of-
sample-extension methods to process new data points. In this paper, we propose a manifold …
sample-extension methods to process new data points. In this paper, we propose a manifold …
Visualizing the phate of neural networks
S Gigante, AS Charles… - Advances in neural …, 2019 - proceedings.neurips.cc
Understanding why and how certain neural networks outperform others is key to guiding
future development of network architectures and optimization methods. To this end, we …
future development of network architectures and optimization methods. To this end, we …
Multiscale anomaly detection using diffusion maps
We propose a multiscale approach to anomaly detection in images, combining spectral
dimensionality reduction and a nearest-neighbor-based anomaly score. We use diffusion …
dimensionality reduction and a nearest-neighbor-based anomaly score. We use diffusion …
A nonlinear and explicit framework of supervised manifold-feature extraction for hyperspectral image classification
P Zhang, H He, L Gao - Neurocomputing, 2019 - Elsevier
Hyperspectral remote sensing has drawn great research interests in earth observation, since
massive and contiguous spectrum can provide rich information of ground objects. However …
massive and contiguous spectrum can provide rich information of ground objects. However …