Spatial Sensitive GRAD-CAM: Visual Explanations for Object Detection by Incorporating Spatial Sensitivity

Visual explanations are important to increase models' transparency. Grad-CAM [1] is an effective method because of its high class discrimination, no requirement of architectural changes, and so on. However, in detection tasks, because Grad-CAM only focuses on the importance of features but does...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE International Conference on Image Processing (ICIP) pp. 256 - 260
Main Authors Yamauchi, Toshinori, Ishikawa, Masayoshi
Format Conference Proceeding
LanguageEnglish
Published IEEE 16.10.2022
Subjects
Computational modeling
Detectors
Feature extraction
Focusing
Grad-CAM
Object detection
Sensitivity
Visual Explanation
Visualization
XAI
Online AccessGet full text

Cover

More Information
Summary:Visual explanations are important to increase models' transparency. Grad-CAM [1] is an effective method because of its high class discrimination, no requirement of architectural changes, and so on. However, in detection tasks, because Grad-CAM only focuses on the importance of features but does not have spatial sensitivity, it generates heatmaps in which not related regions to detected objects are also highlighted. In this study, we propose Spatial Sensitive Grad-CAM (SSGrad-CAM), which can generate appropriate heatmaps for object detectors. SSGrad-CAM modifies the heatmap generated from Grad-CAM with space maps computed by normalizing the magnitude of gradients. In this manner, SSGrad-CAM can incorporate spatial sensitivity and focus on the importance of both features and space. Through experiments, we confirm SSGrad-CAM can generate appropriate heatmaps for detection results, and also confirm it can generate when models detect objects by paying high attention to their peripheral regions, as well.
ISSN:2381-8549
DOI:10.1109/ICIP46576.2022.9897350