Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance

Jung Ho Hong, Woo Jeoung Nam, Kyu Sung Jeon, Seong Whan Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Revealing the transparency of Deep Neural Networks (DNNs) has been widely studied to describe the decision mechanisms of network inner structures. In this paper, we propose a novel post-hoc framework, Unfold and Conquer Attribution Guidance (UCAG), which enhances the explainability of the network decision by spatially scrutinizing the input features with respect to the model confidence. Addressing the phenomenon of missing detailed descriptions, UCAG sequentially complies with the confidence of slices of the image, leading to providing an abundant and clear interpretation. Therefore, it is possible to enhance the representation ability of explanation by preserving the detailed descriptions of assistant input features, which are commonly overwhelmed by the main meaningful regions. We conduct numerous evaluations to validate the performance in several metrics: i) deletion and insertion, ii) (energy-based) pointing games, and iii) positive and negative density maps. Experimental results, including qualitative comparisons, demonstrate that our method outperforms the existing methods with the nature of clear and detailed explanations and applicability.

Original languageEnglish
Title of host publicationAAAI-23 Technical Tracks 7
EditorsBrian Williams, Yiling Chen, Jennifer Neville
PublisherAAAI press
Pages7884-7892
Number of pages9
ISBN (Electronic)9781577358800
Publication statusPublished - 2023 Jun 27
Event37th AAAI Conference on Artificial Intelligence, AAAI 2023 - Washington, United States
Duration: 2023 Feb 72023 Feb 14

Publication series

NameProceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023
Volume37

Conference

Conference37th AAAI Conference on Artificial Intelligence, AAAI 2023
Country/TerritoryUnited States
CityWashington
Period23/2/723/2/14

Bibliographical note

Funding Information:
This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government(MSIT) (No.2022-0-00984, Development of Artificial Intelligence Technology for Personalized Plug-and-Play Explanation and Verification of Explanation & No. 2019-0-00079, Artificial Intelligence Graduate School Program, Korea University)

Publisher Copyright:
Copyright © 2023, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.

ASJC Scopus subject areas

  • Artificial Intelligence

Fingerprint

Dive into the research topics of 'Towards Better Visualizing the Decision Basis of Networks via Unfold and Conquer Attribution Guidance'. Together they form a unique fingerprint.

Cite this