CE-FAM: Concept-Based Explanation via Fusion of Activation Maps

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kuroki, Michihiro, Yamasaki, Toshihiko
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914062047117312
author Kuroki, Michihiro
Yamasaki, Toshihiko
author_facet Kuroki, Michihiro
Yamasaki, Toshihiko
contents Although saliency maps can highlight important regions to explain the reasoning behind image classification in artificial intelligence (AI), the meaning of these regions is left to the user's interpretation. In contrast, conceptbased explanations decompose AI predictions into humanunderstandable concepts, clarifying their contributions. However, few methods can simultaneously reveal what concepts an image classifier learns, which regions are associated with them, and how they contribute to predictions. We propose a novel concept-based explanation method, Concept-based Explanation via Fusion of Activation Maps (CE-FAM). It employs a branched network that shares activation maps with an image classifier and learns to mimic the embeddings of a Vision and Language Model (VLM). The branch network predicts concepts in an image, and their corresponding regions are represented by a weighted sum of activation maps, with weights given by the gradients of the concept prediction scores. Their contributions are quantified based on their impact on the image classification score. Our method provides a general framework for identifying the concept regions and their contributions while leveraging VLM knowledge to handle arbitrary concepts without requiring an annotated dataset. Furthermore, we introduce a novel evaluation metric to assess the accuracy of the concept regions. Our qualitative and quantitative evaluations demonstrate our method outperforms existing approaches and excels in zero-shot inference for unseen concepts.
format Preprint
id arxiv_https___arxiv_org_abs_2509_23849
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CE-FAM: Concept-Based Explanation via Fusion of Activation Maps
Kuroki, Michihiro
Yamasaki, Toshihiko
Computer Vision and Pattern Recognition
Although saliency maps can highlight important regions to explain the reasoning behind image classification in artificial intelligence (AI), the meaning of these regions is left to the user's interpretation. In contrast, conceptbased explanations decompose AI predictions into humanunderstandable concepts, clarifying their contributions. However, few methods can simultaneously reveal what concepts an image classifier learns, which regions are associated with them, and how they contribute to predictions. We propose a novel concept-based explanation method, Concept-based Explanation via Fusion of Activation Maps (CE-FAM). It employs a branched network that shares activation maps with an image classifier and learns to mimic the embeddings of a Vision and Language Model (VLM). The branch network predicts concepts in an image, and their corresponding regions are represented by a weighted sum of activation maps, with weights given by the gradients of the concept prediction scores. Their contributions are quantified based on their impact on the image classification score. Our method provides a general framework for identifying the concept regions and their contributions while leveraging VLM knowledge to handle arbitrary concepts without requiring an annotated dataset. Furthermore, we introduce a novel evaluation metric to assess the accuracy of the concept regions. Our qualitative and quantitative evaluations demonstrate our method outperforms existing approaches and excels in zero-shot inference for unseen concepts.
title CE-FAM: Concept-Based Explanation via Fusion of Activation Maps
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.23849