Band Selection via Explanations From Convolutional Neural Networks

Band Selection via Explanations From Convolutional Neural Networks

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 activ...

Full description

Bibliographic Details
Main Authors: Lei Zhao, Yi Zeng, Peng Liu, Guojin He
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Explainability of CNN
hyperspectral
gradient-weighted class activation
guided backpropagation
band selection
Online Access:https://ieeexplore.ieee.org/document/9040911/

Internet

https://ieeexplore.ieee.org/document/9040911/

Similar Items