对抗样本三元组约束的度量学习算法

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。

Metric learning algorithm with adversarial sample triples constraints

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.