Deep Integrated Explanations

Oren Barkan, Yehonathan Elisha, Jonathan Weill, Yuval Asher, Amit Eshel, Noam Koenigstein

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents Deep Integrated Explanations (DIX) - a universal method for explaining vision models. DIX generates explanation maps by integrating information from the intermediate representations of the model, coupled with their corresponding gradients. Through an extensive array of both objective and subjective evaluations spanning diverse tasks, datasets, and model configurations, we showcase the efficacy of DIX in generating faithful and accurate explanation maps, while surpassing current state-of-the-art methods. Our code is available at: https://github.com/dix-cikm23/dix.

Original languageEnglish
Title of host publicationCIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
PublisherAssociation for Computing Machinery
Pages57-67
Number of pages11
ISBN (Electronic)9798400701245
DOIs
StatePublished - 21 Oct 2023
Event32nd ACM International Conference on Information and Knowledge Management, CIKM 2023 - Birmingham, United Kingdom
Duration: 21 Oct 202325 Oct 2023

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Conference

Conference32nd ACM International Conference on Information and Knowledge Management, CIKM 2023
Country/TerritoryUnited Kingdom
CityBirmingham
Period21/10/2325/10/23

Keywords

  • Computer Vision
  • Deep Learning
  • Explainable AI

Fingerprint

Dive into the research topics of 'Deep Integrated Explanations'. Together they form a unique fingerprint.

Cite this