Deep Integrated Explanations

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

doi:10.1145/3583780.3614836

Deep Integrated Explanations

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

פרסום מחקרי: פרק בספר / בדוח / בכנס › פרסום בספר כנס › ביקורת עמיתים

תקציר

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.

שפה מקורית	אנגלית
כותר פרסום המארח	CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
מוציא לאור	Association for Computing Machinery
עמודים	57-67
מספר עמודים	11
מסת"ב (אלקטרוני)	9798400701245
מזהי עצם דיגיטלי (DOIs)	https://doi.org/10.1145/3583780.3614836
סטטוס פרסום	פורסם - 21 אוק׳ 2023
פורסם באופן חיצוני	כן
אירוע	32nd ACM International Conference on Information and Knowledge Management, CIKM 2023 - Birmingham, בריטניה משך הזמן: 21 אוק׳ 2023 → 25 אוק׳ 2023

סדרות פרסומים

שם	International Conference on Information and Knowledge Management, Proceedings

כנס

כנס	32nd ACM International Conference on Information and Knowledge Management, CIKM 2023
מדינה/אזור	בריטניה
עיר	Birmingham
תקופה	21/10/23 → 25/10/23

הערה ביבליוגרפית

Publisher Copyright:
© 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

גישה למסמך

10.1145/3583780.3614836

קבצים וקישורים אחרים

Link to publication in Scopus

פורמט ציטוט ביבליוגרפי

Barkan, O., Elisha, Y., Weill, J., Asher, Y., Eshel, A., & Koenigstein, N. (2023). Deep Integrated Explanations. ב- CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management (עמודים 57-67). (International Conference on Information and Knowledge Management, Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3583780.3614836

@inproceedings{331be1fdb57b43f1b721a2994731f937,

title = "Deep Integrated Explanations",

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.",

keywords = "Computer Vision, Deep Learning, Explainable AI",

author = "Oren Barkan and Yehonathan Elisha and Jonathan Weill and Yuval Asher and Amit Eshel and Noam Koenigstein",

note = "Publisher Copyright: {\textcopyright} 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.; 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023 ; Conference date: 21-10-2023 Through 25-10-2023",

year = "2023",

month = oct,

day = "21",

doi = "10.1145/3583780.3614836",

language = "אנגלית",

series = "International Conference on Information and Knowledge Management, Proceedings",

publisher = "Association for Computing Machinery",

pages = "57--67",

booktitle = "CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management",

}

Barkan, O, Elisha, Y, Weill, J, Asher, Y, Eshel, A & Koenigstein, N 2023, Deep Integrated Explanations. ב- CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, Association for Computing Machinery, עמודים 57-67, 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023, Birmingham, בריטניה, 21/10/23. https://doi.org/10.1145/3583780.3614836

Deep Integrated Explanations. / Barkan, Oren; Elisha, Yehonathan; Weill, Jonathan et al.
CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2023. עמוד 57-67 (International Conference on Information and Knowledge Management, Proceedings).

פרסום מחקרי: פרק בספר / בדוח / בכנס › פרסום בספר כנס › ביקורת עמיתים

TY - GEN

T1 - Deep Integrated Explanations

AU - Barkan, Oren

AU - Elisha, Yehonathan

AU - Weill, Jonathan

AU - Asher, Yuval

AU - Eshel, Amit

AU - Koenigstein, Noam

PY - 2023/10/21

Y1 - 2023/10/21

N2 - 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.

AB - 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.

KW - Computer Vision

KW - Deep Learning

KW - Explainable AI

UR - http://www.scopus.com/inward/record.url?scp=85175686880&partnerID=8YFLogxK

U2 - 10.1145/3583780.3614836

DO - 10.1145/3583780.3614836

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

AN - SCOPUS:85175686880

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 57

EP - 67

BT - CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management

PB - Association for Computing Machinery

T2 - 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023

Y2 - 21 October 2023 through 25 October 2023

ER -

Barkan O, Elisha Y, Weill J, Asher Y, Eshel A, Koenigstein N. Deep Integrated Explanations. ב- CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2023. עמוד 57-67. (International Conference on Information and Knowledge Management, Proceedings). doi: 10.1145/3583780.3614836

Deep Integrated Explanations

תקציר

סדרות פרסומים

כנס

הערה ביבליוגרפית

גישה למסמך

קבצים וקישורים אחרים

טביעת אצבע

פורמט ציטוט ביבליוגרפי