6533b837fe1ef96bd12a260b
RESEARCH PRODUCT
Manifold Learning with High Dimensional Model Representations
Gustau Camps-vallsGulsen Taskinsubject
Computer sciencebusiness.industryNonlinear dimensionality reductionHyperspectral imaging020206 networking & telecommunicationsPattern recognition02 engineering and technologyFunction (mathematics)ManifoldNonlinear systemKernel (linear algebra)Transformation (function)0202 electrical engineering electronic engineering information engineeringEmbedding020201 artificial intelligence & image processingArtificial intelligencebusinessdescription
Manifold learning methods are very efficient methods for hyperspectral image (HSI) analysis but, unless specifically designed, they cannot provide an explicit embedding map readily applicable to out-of-sample data. A common assumption to deal with the problem is that the transformation between the high input dimensional space and the (typically low) latent space is linear. This is a particularly strong assumption, especially when dealing with hyperspectral images due to the well-known nonlinear nature of the data. To address this problem, a manifold learning method based on High Dimensional Model Representation (HDMR) is proposed, which enables to present a nonlinear embedding function to project out-of-sample samples into the latent space. The proposed method is compared to its linear counterparts and achieves promising performance in terms of classification accuracy of hyperspectral images.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2020-09-26 | IGARSS 2020 - 2020 IEEE International Geoscience and Remote Sensing Symposium |