This problem is addressed using semi-supervised learning and manifold learning, which both exploit the information provided by unlabeled samples in the image. A ...
A spatially adaptive classification method that uses Laplacian regularization is proposed, with the updating scheme using a combination of labeled and unlabeled ...
Spatially Adapted Manifold Learning for Classification of Hyperspectral Imagery with Insufficient Labeled Data · Wonkook KimM. CrawfordJoydeep Ghosh. Computer ...
People also ask
What are the problems with hyperspectral image classification?
What is the spatial resolution of hyperspectral imaging?
An adaptive classification framework is proposed, whereby a kernel machine is first trained with labeled data and then iteratively adapted to new data using ...
Feb 28, 2019 · One major challenge of designing deep learning systems for hyperspectral data classification is the lack of labeled training samples.
Missing: Insufficient | Show results with:Insufficient
This paper reviews current methods that handle labeled data insufficiency and the current feature learning methods for HSI classification using DCNNs.
Missing: Manifold | Show results with:Manifold
... Spatially adapted manifold learning for classification of hyperspectral imagery with insufficient labeled data. In: IEEE International Geoscience and Remote ...
G. Jun, and J. Ghosh, Spatially adaptive classification of hyperspectral data with Gaussian processes, In IEEE International Geoscience and Remote Sensing ...
Ghosh, “Spatially adapted manifold learning for classification of hyperspectral imagery with insufficient labeled data,” in IEEE International Geoscience ...
In this paper, we propose to integrate spectral-spatial information for hyperspectral image classification and exploit the benefits of using spatial features.
Missing: Manifold | Show results with:Manifold