Sorry, you need to enable JavaScript to visit this website.

INTEGRATED GRAD-CAM: SENSITIVITY-AWARE VISUAL EXPLANATION OF DEEP CONVOLUTIONAL NETWORKS VIA INTEGRATED GRADIENT-BASED SCORING

Citation Author(s):
Sam Sattarzadeh, Mahesh Sudhakar, Konstantinos N. Plataniotis, Jongseong Jang, Yeonjeong Jeong, Hyunwoo Kim
Submitted by:
Mahesh Sudhakar
Last updated:
28 June 2021 - 12:40pm
Document Type:
Presentation Slides
Document Year:
2021
Event:

Abstract 

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 under-estimates 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.

up
0 users have voted:

Dataset Files

Presentation slide deck of IGCAM XAI algorithm

(26)

Poster of IGCAM XAI algorithm

(39)