Significance of Softmax-Based Features in Comparison to Distance Metric Learning-Based Features

被引：36

作者：

Horiguchi, Shota ^{[1
]}

Ikami, Daiki ^{[1
]}

Aizawa, Kiyoharu ^{[1
]}

机构：

[1] Univ Tokyo, Dept Informat & Commun Engn, Bunkyo Ku, Tokyo 1338656, Japan

来源：

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE | 2020年 / 42卷 / 05期

关键词：

Feature extraction; Measurement; Principal component analysis; Dimensionality reduction; Network architecture; Automobiles; Task analysis; Deep learning; distance metric learning; classification; retrieval;

D O I：

10.1109/TPAMI.2019.2911075

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

End-to-end distance metric learning (DML) has been applied to obtain features useful in many computer vision tasks. However, these DML studies have not provided equitable comparisons between features extracted from DML-based networks and softmax-based networks. In this paper, we present objective comparisons between these two approaches under the same network architecture.

引用

页码：1279 / 1285

页数：7

共 32 条

[1]

[Anonymous], 2008, Introduction to information retrieval

[2]

[Anonymous], 2006 IEEE COMP VIS P, DOI 10.1109/CVPR.2006.100

[3] Neural Codes for Image Retrieval [J].

Babenko, Artem ;

Slesarev, Anton ;

Chigorin, Alexandr ;

Lempitsky, Victor .

COMPUTER VISION - ECCV 2014, PT I, 2014, 8689 :584-599

[4] Learning visual similarity for product design with convolutional neural networks [J].

Bell, Sean ;

Bala, Kavita .

ACM TRANSACTIONS ON GRAPHICS, 2015, 34 (04)

[5]

Bromley J., 1993, International Journal of Pattern Recognition and Artificial Intelligence, V7, P669, DOI 10.1142/S0218001493000339

[6] Learning Aligned Cross-Modal Representations from Weakly Aligned Data [J].

Castrejon, Lluis ;

Aytar, Yusuf ;

Vondrick, Carl ;

Pirsiavash, Hamed ;

Torralba, Antonio .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :2940-2949

[7]

Chechik G, 2010, J MACH LEARN RES, V11, P1109

[8] Learning a similarity metric discriminatively, with application to face verification [J].

Chopra, S ;

Hadsell, R ;

LeCun, Y .

2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, :539-546

[9]

Donahue J, 2014, PR MACH LEARN RES, V32

[10] 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

← 1 2 3 4 →