Band Selection via Explanations From Convolutional Neural Networks

Abstract

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.

Study on the Classification Method of Rice Leaf Blast Levels Based on Fusion Features and Adaptive-Weight Immune Particle Swarm Optimization Extreme Learning Machine Algorithm

“…In terms of disease spectral feature extraction, spectral data dimensionality reduction is mainly divided into two types of feature extraction and wavelength screening. However, since the feature extraction methods are obtained by a combination of linear or nonlinear methods, the physical information of the original spectrum is corrupted to some extent (Zhao et al, 2020a). The wavelength screening method can directly screen the characteristic wavelengths associated with the disease from the spectral dimension, which can reduce the data dimension and reduce the correlation between wavelengths (Zhao et al, 2020b).…”

Building a Scalable and Interpretable Bayesian Deep Learning Framework for Quality Control of Free Form Surfaces

“…This lack of transparency when coupled with costly actions driven by them result that such models are not being adopted at scale. Various methodologies such as Gradient-based class activation maps that can integrate deep learning estimates with the required transparency have been proposed [21]- [23]. Bayesian deep learning [5] has been proposed to integrate confidence and uncertainty measures with root cause estimates but there is a need for frameworks within MAS that can provide interpretability while accounting for context and confidence.…”

Early Detection of Rice Leaf Blast Disease Using Unmanned Aerial Vehicle Remote Sensing: A Novel Approach Integrating a New Spectral Vegetation Index and Machine Learning

“…However, this method destroys the physical properties of the original spectra to some extent during the linear or nonlinear compression process. At the same time, the practicality of data compression may be limited by the method's computerized system (the original spectral data still need to be acquired during the application process), which greatly restricts its practical popularization and application for crop disease detection at different scales [2,13]. Different from feature compression, to extract disease feature information, feature wavelength screening does not change the original spectral data and only screens a few or dozens of spectral wavelength data containing the main key disease features from the original spectral data, which reduces the data dimensionality and has strong interpretability [14,15].…”