对抗样本三元组约束的度量学习算法

PDF下载HTML

Title:

Metric learning algorithm with adversarial sample triples constraints

作者:

王鑫¹, 郭鑫垚¹, 魏巍^1,2, 梁吉业^1,2

1. 山西大学 计算机与信息技术学院，山西 太原 030006;
2. 山西大学 计算智能与中文信息处理教育部重点实验室，山西 太原 030006

Author(s):

WANG Xin¹, GUO Xinyao¹, WEI Wei^1,2, LIANG Jiye^1,2

1. School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China;
2. Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education, Shanxi University, Taiyuan 030006, China

关键词:

机器学习; 度量学习; 三元组约束; 对抗训练; 马氏距离; 样本扰动; 凸优化; 梯度下降

Keywords:

machine learning; metric learning; triplet constraints; adversarial training; Mahalanobis distance; sample perturbation; convex optimization; gradient descent

分类号:

TP181

DOI:

10.11992/tis.202009050

摘要:

针对已有三元组约束的度量学习算法大多利用先验知识构建约束，一定程度上制约了度量学习算法性能的问题，本文借鉴对抗训练中样本扰动的思想，在原始样本附近学习对抗样本以构造对抗三元组约束，基于对抗三元组和原始三元组约束构建了度量学习模型，提出了对抗样本三元组约束的度量学习算法(metric learning algorithm with adversarial sample triples constraints，ASTCML)。实验结果表明，提出的算法既克服了已有固定约束方法受先验知识影响大的问题，也提高了分类精度，说明区分更加难以区分的三元组约束能够提升算法的性能。

Abstract:

Most of the existing metric learning algorithms with triple constraints use prior knowledge to construct constraints, which restricts the performance of metric learning algorithms to a certain extent. To solve this problem, the metric learning algorithm with adversarial sample triple constraints, named ASTCML, is proposed based on the idea of sample perturbation in adversarial training, in which the adversarial sample is learned near the original sample to construct adversarial triple constraints. The metric learning model is constructed on the basis of adversarial triples and original triples constraints. Experimental results show that the proposed algorithm overcomes the effect of prior knowledge that is problematic for existing fixed constraint methods and improves the classification accuracy. This shows that distinguishing triple constraints that are more difficult to distinguish can improve the performance of the algorithm.