Enhancing Deep Neural Network Saliency Visualizations With Gradual Extrapolation

Enhancing Deep Neural Network Saliency Visualizations With Gradual Extrapolation

In this paper, an enhancement technique for the class activation mapping methods such as gradient-weighted class activation maps or excitation backpropagation is proposed to present the visual explanations of decisions from convolutional neural network-based models. The proposed idea, called Gradual...

Full description

Bibliographic Details
Main Author: Tomasz Szandala
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Deep neural networks
backpropagation algorithms
computer vision
explainable artificial intelligence
XAI
visualization
Online Access:https://ieeexplore.ieee.org/document/9468713/

Internet

https://ieeexplore.ieee.org/document/9468713/

Similar Items