Visual Explanations via Iterated Integrated Attributions

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

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


We introduce Iterated Integrated Attributions (IIA) - a generic method for explaining the predictions of vision models. IIA employs iterative integration across the input image, the internal representations generated by the model, and their gradients, yielding precise and focused explanation maps. We demonstrate the effectiveness of IIA through comprehensive evaluations across various tasks, datasets, and network architectures. Our results showcase that IIA produces accurate explanation maps, outperforming other state-of-the-art explanation techniques.

Original languageEnglish
Title of host publicationProceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages12
ISBN (Electronic)9798350307184
StatePublished - 2023
Externally publishedYes
Event2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 - Paris, France
Duration: 2 Oct 20236 Oct 2023

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
ISSN (Print)1550-5499


Conference2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023

Bibliographical note

Publisher Copyright:
© 2023 IEEE.


Dive into the research topics of 'Visual Explanations via Iterated Integrated Attributions'. Together they form a unique fingerprint.

Cite this