Understanding CNNs from excitations

05/02/2022
by   Zijian Ying, et al.
0

For instance-level explanation, in order to reveal the relations between high-level semantics and detailed spatial information, this paper proposes a novel cognitive approach to neural networks, which named PANE. Under the guidance of PANE, a novel saliency map representation method, named IOM, is proposed for CNN-like models. We make the comparison with eight state-of-the-art saliency map representation methods. The experimental results show that IOM far outperforms baselines. The work of this paper may bring a new perspective to understand deep neural networks.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset