GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps

Oren Barkan, Omri Armstrong, Amir Hertz, Avi Caciularu, Ori Katz, Itzik Malkiel, Noam Koenigstein

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

10 Scopus citations

Abstract

We present Gradient Activation Maps (GAM) - a machinery for explaining predictions made by visual similarity and classification models. By gleaning localized gradient and activation information from multiple network layers, GAM offers improved visual explanations, when compared to existing alternatives. The algorithmic advantages of GAM are explained in detail, and validated empirically, where it is shown that GAM outperforms its alternatives across various tasks and datasets.

Original languageEnglish
Title of host publicationCIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management
Pages68-77
Number of pages10
ISBN (Electronic)9781450384469
DOIs
StatePublished - 26 Oct 2021
Externally publishedYes
Event30th ACM International Conference on Information and Knowledge Management, CIKM 2021 - Virtual, Online, Australia
Duration: 1 Nov 20215 Nov 2021

Publication series

NameInternational Conference on Information and Knowledge Management, Proceedings

Conference

Conference30th ACM International Conference on Information and Knowledge Management, CIKM 2021
Country/TerritoryAustralia
CityVirtual, Online
Period1/11/215/11/21

Keywords

  • deep learning
  • explainable & interpretable ai
  • saliency maps

Fingerprint

Dive into the research topics of 'GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps'. Together they form a unique fingerprint.

Cite this