GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps

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

doi:10.1145/3459637.3482430

GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps

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

מדעי המחשב

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

תקציר

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.

שפה מקורית	אנגלית
כותר פרסום המארח	CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management
מוציא לאור	Association for Computing Machinery
עמודים	68-77
מספר עמודים	10
מסת"ב (אלקטרוני)	9781450384469
מזהי עצם דיגיטלי (DOIs)	https://doi.org/10.1145/3459637.3482430
סטטוס פרסום	פורסם - 26 אוק׳ 2021
אירוע	30th ACM International Conference on Information and Knowledge Management, CIKM 2021 - Virtual, Online, אוסטרליה משך הזמן: 1 נוב׳ 2021 → 5 נוב׳ 2021

סדרות פרסומים

שם	International Conference on Information and Knowledge Management, Proceedings

כנס

כנס	30th ACM International Conference on Information and Knowledge Management, CIKM 2021
מדינה/אזור	אוסטרליה
עיר	Virtual, Online
תקופה	1/11/21 → 5/11/21

הערה ביבליוגרפית

Publisher Copyright:
© 2021 ACM.

גישה למסמך

10.1145/3459637.3482430

קבצים וקישורים אחרים

Link to publication in Scopus

פורמט ציטוט ביבליוגרפי

Barkan, O., Armstrong, O., Hertz, A., Caciularu, A., Katz, O., Malkiel, I., & Koenigstein, N. (2021). GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps. ב- CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management (עמודים 68-77). (International Conference on Information and Knowledge Management, Proceedings). Association for Computing Machinery. https://doi.org/10.1145/3459637.3482430

Barkan, Oren ; Armstrong, Omri ; Hertz, Amir et al. / GAM : Explainable Visual Similarity and Classification via Gradient Activation Maps. CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2021. עמודים 68-77 (International Conference on Information and Knowledge Management, Proceedings).

@inproceedings{01298076dd51406a9aecd41c2204a2ac,

title = "GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps",

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.",

keywords = "deep learning, explainable & interpretable ai, saliency maps",

author = "Oren Barkan and Omri Armstrong and Amir Hertz and Avi Caciularu and Ori Katz and Itzik Malkiel and Noam Koenigstein",

note = "Publisher Copyright: {\textcopyright} 2021 ACM.; 30th ACM International Conference on Information and Knowledge Management, CIKM 2021 ; Conference date: 01-11-2021 Through 05-11-2021",

year = "2021",

month = oct,

day = "26",

doi = "10.1145/3459637.3482430",

language = "אנגלית",

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

publisher = "Association for Computing Machinery",

pages = "68--77",

booktitle = "CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management",

}

Barkan, O, Armstrong, O, Hertz, A, Caciularu, A, Katz, O, Malkiel, I & Koenigstein, N 2021, GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps. ב- CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management. International Conference on Information and Knowledge Management, Proceedings, Association for Computing Machinery, עמודים 68-77, 30th ACM International Conference on Information and Knowledge Management, CIKM 2021, Virtual, Online, אוסטרליה, 1/11/21. https://doi.org/10.1145/3459637.3482430

GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps. / Barkan, Oren; Armstrong, Omri; Hertz, Amir et al.
CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery, 2021. עמוד 68-77 (International Conference on Information and Knowledge Management, Proceedings).

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

TY - GEN

T1 - GAM

T2 - 30th ACM International Conference on Information and Knowledge Management, CIKM 2021

AU - Barkan, Oren

AU - Armstrong, Omri

AU - Hertz, Amir

AU - Caciularu, Avi

AU - Katz, Ori

AU - Malkiel, Itzik

AU - Koenigstein, Noam

PY - 2021/10/26

Y1 - 2021/10/26

N2 - 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.

AB - 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.

KW - deep learning

KW - explainable & interpretable ai

KW - saliency maps

UR - http://www.scopus.com/inward/record.url?scp=85119175338&partnerID=8YFLogxK

U2 - 10.1145/3459637.3482430

DO - 10.1145/3459637.3482430

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

AN - SCOPUS:85119175338

T3 - International Conference on Information and Knowledge Management, Proceedings

SP - 68

EP - 77

BT - CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management

PB - Association for Computing Machinery

Y2 - 1 November 2021 through 5 November 2021

ER -

Barkan O, Armstrong O, Hertz A, Caciularu A, Katz O, Malkiel I et al. GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps. ב- CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2021. עמוד 68-77. (International Conference on Information and Knowledge Management, Proceedings). doi: 10.1145/3459637.3482430

GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps

תקציר

סדרות פרסומים

כנס

הערה ביבליוגרפית

גישה למסמך

קבצים וקישורים אחרים

טביעת אצבע

פורמט ציטוט ביבליוגרפי