GAM: Explainable Visual Similarity and Classification via Gradient Activation Maps

被引：9

作者：

Barkan, Oren ^{[1
,2
]}

Armstrong, Omri ^{[3
]}

Hertz, Amir ^{[2
]}

Caciularu, Avi ^{[4
]}

Katz, Ori ^{[2
,5
]}

Malkiel, Itzik ^{[2
,3
]}

Koenigstein, Noam ^{[2
,3
]}

机构：

[1] Open Univ, Raanana, Israel

[2] Microsoft, Tel Aviv, Israel

[3] Tel Aviv Univ, Tel Aviv, Israel

[4] Bar Ilan Univ, Ramat Gan, Israel

[5] Technion, Haifa, Israel

来源：

PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021 | 2021年

关键词：

Explainable & Interpretable AI; Deep Learning; Saliency Maps;

D O I：

10.1145/3459637.3482430

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

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.

引用

页码：68 / 77

页数：10

共 32 条

[1]

Adebayo J., 2018, Advances in Neural Information Processing Systems

[2]

Barkan Oren, 2021, P ACM INT C CIKM INF

[3]

Ben-Baruch E, 2021, Arxiv, DOI arXiv:2009.14119

[4] Grad-CAM plus plus : Generalized Gradient-based Visual Explanations for Deep Convolutional Networks [J].

Chattopadhay, Aditya ;

Sarkar, Anirban ;

Howlader, Prantik ;

Balasubramanian, Vineeth N. .

2018 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION (WACV 2018), 2018, :839-847

[5]

Chen L, 2020, IEEE WINT CONF APPL, P2783, DOI [10.1109/WACV45572.2020.9093461, 10.1109/wacv45572.2020.9093461]

[6]

Doshi-Velez F., 2017, Towards a rigorous science of interpretable machine learning, DOI [10.2139/ssrn.3064761, DOI 10.2139/SSRN.3064761]

[7] The Pascal Visual Object Classes (VOC) Challenge [J].

Everingham, Mark ;

Van Gool, Luc ;

Williams, Christopher K. I. ;

Winn, John ;

Zisserman, Andrew .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2010, 88 (02) :303-338

[8] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[9] Deep Metric Learning Using Triplet Network [J].

Hoffer, Elad ;

Ailon, Nir .

SIMILARITY-BASED PATTERN RECOGNITION, SIMBAD 2015, 2015, 9370 :84-92

[10] Densely Connected Convolutional Networks [J].

Huang, Gao ;

Liu, Zhuang ;

van der Maaten, Laurens ;

Weinberger, Kilian Q. .

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :2261-2269

← 1 2 3 4 →