Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networks

05/20/2020
by   Zifan Wang, et al.
0

Recently, increasing attention has been drawn to the internal mechanisms of convolutional neural networks, and the reason why the network makes specific decisions. In this paper, we develop a novel post-hoc visual explanation method called Score-CAM based on class activation mapping. Unlike previous class activation mapping based approaches, Score-CAM gets rid of the dependence on gradients by obtaining the weight of each activation map through its forward passing score on target class, the final result is obtained by a linear combination of weights and activation maps. We demonstrate that Score-CAM achieves better visual performance with less noise and is fairer than Grad-CAM and Grad-CAM++ for interpreting the decision making process. Our approach outperforms previous methods on both recognition and localization tasks, it also passes the sanity check. We also indicate its application as debugging tools. Official code will be released soon.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 5

page 6

page 7

page 8

page 10

page 11

10/03/2019

Score-CAM:Improved Visual Explanations Via Score-Weighted Class Activation Mapping

Recently, more and more attention has been drawn into the internal mecha...
02/10/2021

LIFT-CAM: Towards Better Explanations for Class Activation Mapping

Increasing demands for understanding the internal behaviors of convoluti...
03/25/2021

Group-CAM: Group Score-Weighted Visual Explanations for Deep Convolutional Networks

In this paper, we propose an efficient saliency map generation method, c...
10/30/2017

Grad-CAM++: Generalized Gradient-based Visual Explanations for Deep Convolutional Networks

Over the last decade, Convolutional Neural Network (CNN) models have bee...
01/17/2020

Adapting Grad-CAM for Embedding Networks

The gradient-weighted class activation mapping (Grad-CAM) method can fai...
11/13/2017

Learning and Visualizing Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled Holes

3D Convolutional Neural Networks (3D-CNN) have been used for object reco...
05/31/2018

Respond-CAM: Analyzing Deep Models for 3D Imaging Data by Visualizations

The convolutional neural network (CNN) has become a powerful tool for va...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.