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

被引：33

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] Neural Codes for Image Retrieval
Babenko, Artem
Slesarev, Anton
Chigorin, Alexandr
Lempitsky, Victor
[J]. COMPUTER VISION - ECCV 2014, PT I, 2014, 8689 : 584 - 599
[2] Learning visual similarity for product design with convolutional neural networks
Bell, Sean
Bala, Kavita
[J]. ACM TRANSACTIONS ON GRAPHICS, 2015, 34 (04):
[3] Bromley J., 1993, International Journal of Pattern Recognition and Artificial Intelligence, V7, P669, DOI 10.1142/S0218001493000339
[4] Learning Aligned Cross-Modal Representations from Weakly Aligned Data
Castrejon, Lluis
Aytar, Yusuf
Vondrick, Carl
Pirsiavash, Hamed
Torralba, Antonio
[J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 2940 - 2949
[5] Chechik G, 2010, J MACH LEARN RES, V11, P1109
[6] Learning a similarity metric discriminatively, with application to face verification
Chopra, S
Hadsell, R
LeCun, Y
[J]. 2005 IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOL 1, PROCEEDINGS, 2005, : 539 - 546
[7] Donahue J, 2014, PR MACH LEARN RES, V32
[8] Deep Residual Learning for Image Recognition
He, Kaiming
Zhang, Xiangyu
Ren, Shaoqing
Sun, Jian
[J]. 2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, : 770 - 778
[9] Deep Metric Learning Using Triplet Network
Hoffer, Elad
Ailon, Nir
[J]. SIMILARITY-BASED PATTERN RECOGNITION, SIMBAD 2015, 2015, 9370 : 84 - 92
[10] Product Quantization for Nearest Neighbor Search
Jegou, Herve
Douze, Matthijs
Schmid, Cordelia
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2011, 33 (01) : 117 - 128

← 1 2 3 4 →