Saved in:
Bibliographic Details
Main Authors: Rong, Yao, Scheerer, David, Kasneci, Enkelejda
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.13032
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909210919305216
author Rong, Yao
Scheerer, David
Kasneci, Enkelejda
author_facet Rong, Yao
Scheerer, David
Kasneci, Enkelejda
contents In recent years, model explanation methods have been designed to interpret model decisions faithfully and intuitively so that users can easily understand them. In this paper, we propose a framework, Faithful Attention Explainer (FAE), capable of generating faithful textual explanations regarding the attended-to features. Towards this goal, we deploy an attention module that takes the visual feature maps from the classifier for sentence generation. Furthermore, our method successfully learns the association between features and words, which allows a novel attention enforcement module for attention explanation. Our model achieves promising performance in caption quality metrics and a faithful decision-relevance metric on two datasets (CUB and ACT-X). In addition, we show that FAE can interpret gaze-based human attention, as human gaze indicates the discriminative features that humans use for decision-making, demonstrating the potential of deploying human gaze for advanced human-AI interaction.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13032
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Faithful Attention Explainer: Verbalizing Decisions Based on Discriminative Features
Rong, Yao
Scheerer, David
Kasneci, Enkelejda
Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
In recent years, model explanation methods have been designed to interpret model decisions faithfully and intuitively so that users can easily understand them. In this paper, we propose a framework, Faithful Attention Explainer (FAE), capable of generating faithful textual explanations regarding the attended-to features. Towards this goal, we deploy an attention module that takes the visual feature maps from the classifier for sentence generation. Furthermore, our method successfully learns the association between features and words, which allows a novel attention enforcement module for attention explanation. Our model achieves promising performance in caption quality metrics and a faithful decision-relevance metric on two datasets (CUB and ACT-X). In addition, we show that FAE can interpret gaze-based human attention, as human gaze indicates the discriminative features that humans use for decision-making, demonstrating the potential of deploying human gaze for advanced human-AI interaction.
title Faithful Attention Explainer: Verbalizing Decisions Based on Discriminative Features
topic Computation and Language
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.13032