Manifold-Learning-Based Feature Extraction for Classification of Hyperspectral Data: A Review of Advances in Manifold Learning

By Dalton D. Lunga, Saurabh Prasad, Melba M. Crawford, Okan K. Ersoy. 2014

292 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Ecology, 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 Artificial Intelligence

1. Tom Zahavy
2. Nir Ben-Zrihem
3. Shie Mannor
4. Xiuping Jia
5. Matteo Matteucci
6. Sara Comai
7. Renlong Hang
8. Shihong Du

In Ecology

1. Wenzhi Zhao
2. Shihong Du
3. Xiuping Jia
4. Matteo Matteucci
5. Sara Comai
6. Sen Jia
7. Pedram Ghamisi
8. Danfeng Hong

In Media Technology

1. Pedram Ghamisi
2. Yushi Chen
3. Danfeng Hong
4. Matteo Matteucci
5. Sara Comai
6. Ava Vali
7. Antonio J. Plaza
8. Renlong Hang

Citations in the corpus

• Graying the black box: Understanding DQNs (2016, methodology): “It has been proven to outperform linear dimensionality reduction methods and non-linear embedding methods such as ISOMAP (Tenenbaum et al., 2000) in several research fields including machine-learning benchmark datasets and hyper-spectral remote sensing data (Lunga et al., 2014).”
• Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks (2016, background): “, vegetation), hyperspectral data are inherently nonlinear [10], [11], which make linear transformation-based methods not that suitable for the analysis of such data.”
• Spectral–Spatial Feature Extraction for Hyperspectral Image Classification: A Dimension Reduction and Deep Learning Approach (2016, background): “However, in the field of HSI classification, instead of containing global mutual information, discriminative projections for each class should be explored [13].”
• Cascaded Recurrent Neural Networks for Hyperspectral Image Classification (2017, methodology): “Popular models include principle component analysis, linear discriminant analysis (LDA) [6]–[8], and graph embedding [9]–[11].”
• Deep Learning for Land Use and Land Cover Classification Based on Hyperspectral and Multispectral Earth Observation Data: A Review (2020, background): “[79] underline the advantages of using supervised algorithms, pointing out that not only the global mutual information but also the in-class discriminative projections have to be explored in HSI data.”
• A Novel Ranking-Based Clustering Approach for Hyperspectral Band Selection (2016, background): “1, the distribution of the bands is clearly nonspherical (the bands actually live in a low-dimensional manifold [39]).”