Exclusive Feature Constrained Class Activation Mapping for Better Visual Explanation

Exclusive Feature Constrained Class Activation Mapping for Better Visual Explanation

Whereas Deep Neural Network(DNN) shows wonderful performance on large scale data, lacking interpretability limits their usage in scenarios relevant to security. To make visual explanations less noisy and more class-discriminative, in this work, we propose a visual explanation method of DNN, named Ex...

Full description

Bibliographic Details
Main Authors: Pengda Wang, Xiangwei Kong, Weikuo Guo, Xunpeng Zhang
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Interpretability
visual explanation
class activation mapping
interpretability evaluation
Online Access:https://ieeexplore.ieee.org/document/9405672/

Internet

https://ieeexplore.ieee.org/document/9405672/

Similar Items