Faithful Attention Explainer: Verbalizing Decisions Based on Discriminative Features

Yao Rong, David Scheerer, Enkelejda Kasneci

Publikation: Beitrag in FachzeitschriftKonferenzartikelBegutachtung

Abstract

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.

OriginalspracheEnglisch
Seiten (von - bis)33-40
Seitenumfang8
FachzeitschriftCEUR Workshop Proceedings
Jahrgang3793
PublikationsstatusVeröffentlicht - 2024
VeranstaltungJoint of the 2nd World Conference on eXplainable Artificial Intelligence Late-Breaking Work, Demos and Doctoral Consortium, xAI-2024:LB/D/DC - Valletta, Malta
Dauer: 17 Juli 202419 Juli 2024

Fingerprint

Untersuchen Sie die Forschungsthemen von „Faithful Attention Explainer: Verbalizing Decisions Based on Discriminative Features“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren