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

نتاج البحث: فصل من :كتاب / تقرير / مؤتمر › منشور من مؤتمر › مراجعة النظراء

ملخص

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.

اللغة الأصلية	الإنجليزيّة
عنوان منشور المضيف	CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management
ناشر	Association for Computing Machinery
الصفحات	68-77
عدد الصفحات	10
رقم المعيار الدولي للكتب (الإلكتروني)	9781450384469
المعرِّفات الرقمية للأشياء	https://doi.org/10.1145/3459637.3482430
حالة النشر	نُشِر - 26 أكتوبر 2021
الحدث	30th ACM International Conference on Information and Knowledge Management, CIKM 2021 - Virtual, Online, أستراليا المدة: ١ نوفمبر ٢٠٢١ → ٥ نوفمبر ٢٠٢١

سلسلة المنشورات

الاسم	International Conference on Information and Knowledge Management, Proceedings

!!Conference

!!Conference	30th ACM International Conference on Information and Knowledge Management, CIKM 2021
الدولة/الإقليم	أستراليا
المدينة	Virtual, Online
المدة	١/١١/٢١ → ٥/١١/٢١

ملاحظة ببليوغرافية

Publisher Copyright:
© 2021 ACM.

الوصول إلى المستند

10.1145/3459637.3482430

الملفات والروابط الأخرى

Link to publication in Scopus

قم بذكر هذا

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. في CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management (الصفحات 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 وآخرون. / 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. الصفحات 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. في 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, الصفحات 68-77, 30th ACM International Conference on Information and Knowledge Management, CIKM 2021, Virtual, Online, أستراليا, ١/١١/٢١. https://doi.org/10.1145/3459637.3482430

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

نتاج البحث: فصل من :كتاب / تقرير / مؤتمر › منشور من مؤتمر › مراجعة النظراء

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 وآخرون. GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps. في CIKM 2021 - Proceedings of the 30th ACM International Conference on Information and Knowledge Management. Association for Computing Machinery. 2021. صفحة 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

ملخص

سلسلة المنشورات

!!Conference

ملاحظة ببليوغرافية

الوصول إلى المستند

الملفات والروابط الأخرى

بصمة

قم بذكر هذا