Visual Explanations via Iterated Integrated Attributions

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

doi:10.1109/ICCV51070.2023.00198

Visual Explanations via Iterated Integrated Attributions

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

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

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 language	English
Title of host publication	Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2073-2084
Number of pages	12
ISBN (Electronic)	9798350307184
DOIs	https://doi.org/10.1109/ICCV51070.2023.00198
State	Published - 2023
Externally published	Yes
Event	2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 - Paris, France Duration: 2 Oct 2023 → 6 Oct 2023

Publication series

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

Conference

Conference	2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023
Country/Territory	France
City	Paris
Period	2/10/23 → 6/10/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Access to Document

10.1109/ICCV51070.2023.00198

Cite this

Barkan, O., Elisha, Y., Asher, Y., Eshel, A., & Koenigstein, N. (2023). Visual Explanations via Iterated Integrated Attributions. In Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 (pp. 2073-2084). (Proceedings of the IEEE International Conference on Computer Vision). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCV51070.2023.00198

@inproceedings{d3bac99229614ac1ae7aceb5e0a13cad,

title = "Visual Explanations via Iterated Integrated Attributions",

abstract = "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.",

author = "Oren Barkan and Yehonatan Elisha and Yuval Asher and Amit Eshel and Noam Koenigstein",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023 ; Conference date: 02-10-2023 Through 06-10-2023",

year = "2023",

doi = "10.1109/ICCV51070.2023.00198",

language = "אנגלית",

series = "Proceedings of the IEEE International Conference on Computer Vision",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2073--2084",

booktitle = "Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023",

address = "ארצות הברית",

}

Barkan, O, Elisha, Y, Asher, Y, Eshel, A & Koenigstein, N 2023, Visual Explanations via Iterated Integrated Attributions. in Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023. Proceedings of the IEEE International Conference on Computer Vision, Institute of Electrical and Electronics Engineers Inc., pp. 2073-2084, 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023, Paris, France, 2/10/23. https://doi.org/10.1109/ICCV51070.2023.00198

Visual Explanations via Iterated Integrated Attributions. / Barkan, Oren; Elisha, Yehonatan; Asher, Yuval et al.
Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 2073-2084 (Proceedings of the IEEE International Conference on Computer Vision).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Visual Explanations via Iterated Integrated Attributions

AU - Barkan, Oren

AU - Elisha, Yehonatan

AU - Asher, Yuval

AU - Eshel, Amit

AU - Koenigstein, Noam

PY - 2023

Y1 - 2023

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85175598274&partnerID=8YFLogxK

U2 - 10.1109/ICCV51070.2023.00198

DO - 10.1109/ICCV51070.2023.00198

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85175598274

T3 - Proceedings of the IEEE International Conference on Computer Vision

SP - 2073

EP - 2084

BT - Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023

Y2 - 2 October 2023 through 6 October 2023

ER -

Barkan O, Elisha Y, Asher Y, Eshel A, Koenigstein N. Visual Explanations via Iterated Integrated Attributions. In Proceedings - 2023 IEEE/CVF International Conference on Computer Vision, ICCV 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 2073-2084. (Proceedings of the IEEE International Conference on Computer Vision). doi: 10.1109/ICCV51070.2023.00198

Visual Explanations via Iterated Integrated Attributions

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this