Abstract

Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model. However, the average gradient-based terms deployed in this method underestimates the contribution of the representations discovered by the model to its predictions. Addressing this problem, we introduce a solution to tackle this issue by computing the path integral of the gradient-based terms in Grad-CAM. We conduct a thorough analysis to demonstrate the improvement achieved by our method in measuring the importance of the extracted representations for the CNN’s predictions, which yields to our method’s administration in object localization and model interpretation.

@INPROCEEDINGS{9415064,
  author={Sattarzadeh, Sam and Sudhakar, Mahesh and Plataniotis, Konstantinos N. and Jang, Jongseong and Jeong, Yeonjeong and Kim, Hyunwoo},
  booktitle={ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, 
  title={Integrated Grad-Cam: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks Via Integrated Gradient-Based Scoring}, 
  year={2021},
  volume={},
  number={},
  pages={1775-1779},
  doi={10.1109/ICASSP39728.2021.9415064}
}