Stochastic Integrated Explanations for Vision Models

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

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

1 Scopus citations

Abstract

We introduce Stochastic Integrated Explanations (SIX) - a general method for explaining predictions made by vision models. SIX employs stochastic integration on the internal representations across different network layers, producing explanation maps at various scales. The primary innovation of SIX is the introduction of randomness to the integration process by modeling the baseline representation as a random tensor. Through iterative sampling from the baseline distribution, SIX generates a diverse set of explanation maps, allowing the selection of the best-performing map based on a specific metric of interest. Extensive evaluations on various model architectures showcase the superior performance of SIX compared to state-of-the-art explanation methods, affirming its effectiveness across multiple metrics. Our code is available at: https://github.com/six-icdm/six

Original languageEnglish
Title of host publicationProceedings - 23rd IEEE International Conference on Data Mining, ICDM 2023
EditorsGuihai Chen, Latifur Khan, Xiaofeng Gao, Meikang Qiu, Witold Pedrycz, Xindong Wu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages938-943
Number of pages6
ISBN (Electronic)9798350307887
DOIs
StatePublished - 2023
Externally publishedYes
Event23rd IEEE International Conference on Data Mining, ICDM 2023 - Shanghai, China
Duration: 1 Dec 20234 Dec 2023

Publication series

NameProceedings - IEEE International Conference on Data Mining, ICDM
ISSN (Print)1550-4786

Conference

Conference23rd IEEE International Conference on Data Mining, ICDM 2023
Country/TerritoryChina
CityShanghai
Period1/12/234/12/23

Keywords

  • Computer Vision
  • Deep Learning
  • Explainable AI

Fingerprint

Dive into the research topics of 'Stochastic Integrated Explanations for Vision Models'. Together they form a unique fingerprint.

Cite this