论文标题
与对抗性三胞胎嵌入的人重新识别
Person Re-identification with Adversarial Triplet Embedding
论文作者
论文摘要
人重新识别是一项重要的任务，并在视频监视中为公共安全提供了广泛的应用。在过去的几年中，三胞胎损失的深度学习网络因这个问题而变得流行。但是，三胞胎的损失通常遭受当地最佳最佳状态的影响，并且在很大程度上依赖于硬采矿的策略。在本文中，我们建议通过一种称为对抗性三重嵌入（ATE）的新的深度度量学习方法来解决这个问题，在该方法中，我们同时生成对抗性三胞胎，并在统一框架中嵌入歧视性特征。特别是，通过将对抗性扰动引入训练过程中来产生对抗性三胞胎。这种对抗性游戏被转换为最小问题，从理论观点具有最佳解决方案。在几个基准数据集上进行的广泛实验证明了该方法对最新文献的有效性。
Person re-identification is an important task and has widespread applications in video surveillance for public security. In the past few years, deep learning network with triplet loss has become popular for this problem. However, the triplet loss usually suffers from poor local optimal and relies heavily on the strategy of hard example mining. In this paper, we propose to address this problem with a new deep metric learning method called Adversarial Triplet Embedding (ATE), in which we simultaneously generate adversarial triplets and discriminative feature embedding in an unified framework. In particular, adversarial triplets are generated by introducing adversarial perturbations into the training process. This adversarial game is converted into a minimax problem so as to have an optimal solution from the theoretical view. Extensive experiments on several benchmark datasets demonstrate the effectiveness of the approach against the state-of-the-art literature.
