Information-Assisted Density Peak Index for Hyperspectral Band Selection

Luo, Xiaoyan; Xue, Rui; Yin, Jingwei

doi:10.1109/lgrs.2017.2741494

Cited by 34 publications

(18 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ii) Distance value: The minimum distance from other points with greater density. Luo et al [52] proposed an information-assisted density peak index (IaDPI) to prioritize hyperspectral bands. In [53], a fast density peak clustering method (FDPC) is introduced into hyperspectral image classification.…”

Section: B Diversity Measurement Methodsmentioning

confidence: 99%

Robust Learning of Mislabeled Training Samples for Remote Sensing Image Scene Classification

Kuang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Section: B Diversity Measurement Methodsmentioning

confidence: 99%

Robust Learning of Mislabeled Training Samples for Remote Sensing Image Scene Classification

Kuang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

“…When obtaining a well-trained CNN, GradHM and Guided-GradHM could be calculated by the training samples. Finally, bands were selected according to with seven known algorithms: the clustering-based band selection algorithm with mutual information (CBBS-MI) [2], the wrapper based algorithm on the SVM (SVMwrapper) [45], the algorithm based on CNN band selection (BSCNN+) [28], WaLuDi [46], MPWR [47] and E-FDPC [48]. Then, we randomly choose 10% of the data to train the SVM classifier in all the methods and obtain the classification accuracy of all methods in different selected bands.…”

Section: B Experimental Setupmentioning

confidence: 99%

Band Selection via Explanations From Convolutional Neural Networks

et al. 2020

View full text Add to dashboard Cite

Band Selection is a research hotspot in the field of hyperspectral imaging (HSI) processing. This paper proposes a method that selects bands for HSI classification by the explainability of a convolutional neural network (CNN). We design a CNN architecture and use its 1D gradient-weighted class activation mapping (GradCAM) to obtain a gradient-weighted heatmap (GradHM) by the last layer in the well-trained CNN. Since the pooling layer in the CNN leads to a dimension change of the GradHM, cubic spline interpolation (CSI) is used to up-sample the GradHM. To further improve the accuracy of the up-sampled GradHM for the important band, guided backpropagation was adopted to obtain a more detailed GradHM (Guided-GradHM). Finally, based on GradHM and Guided-GradHM, two strategies, named Average Selection (AS) and Total Selection (TS), are proposed to form new and different combinations of methods (GradHM+AS, GradHM+TS, Guided-GradHM+AS, and Guided-GradHM+TS). In experiments, the proposed methods show better performance compared to other methods. In most cases, if the selected bands were fewer, then the Guided-GradHM+AS was more credible than the other methods. Furthermore, different datasets were used to validate the proposed methods. INDEX TERMS Explainability of CNN, hyperspectral, gradient-weighted class activation, guided backpropagation, band selection.

show abstract

“…Other approaches include band clustering 35 using various similarity measures and selecting representatives [11,12]. Popular similarity measures include information theoretical measures [13] or the correlation coefficient [14]. More sophisticated algorithms try to evaluate a complete band subset rather than individually ranking the features.…”

Section: Accepted Manuscriptmentioning

confidence: 99%

MIMR-DGSA: Unsupervised hyperspectral band selection based on information theory and a modified discrete gravitational search algorithm

et al. 2019

View full text Add to dashboard Cite

Band selection plays an important role in hyperspectral data analysis as it can improve the performance of data analysis without losing information about the constitution of the underlying data. We propose a MIMR-DGSA algorithm for band selection by following the Maximum-Information-Minimum-Redundancy (MIMR) criterion that maximises the information carried by individual features of a subset and minimises redundant information between them. Subsets are generated with a modified Discrete Gravitational Search Algorithm (DGSA) where we definine a neighbourhood concept for feature subsets. A fast algorithm for pairwise mutual information calculation that incorporates variable bandwidths of hyperspectral bands called VarBWFastMI is also developed. Classification results on three hyperspectral remote sensing datasets show that the proposed MIMR-DGSA performs similar to the original MIMR with Clonal Selection Algorithm (CSA) but is computationally more efficient and easier to

show abstract

Information-Assisted Density Peak Index for Hyperspectral Band Selection

Cited by 34 publications

References 24 publications

Robust Learning of Mislabeled Training Samples for Remote Sensing Image Scene Classification

Robust Learning of Mislabeled Training Samples for Remote Sensing Image Scene Classification

Band Selection via Explanations From Convolutional Neural Networks

MIMR-DGSA: Unsupervised hyperspectral band selection based on information theory and a modified discrete gravitational search algorithm

Contact Info

Product

Resources

About