In this paper, we propose a discriminative sampling method to select most effective negative samples via deep reinforcement learning for kinship verification. Unlike most existing facial kinship verification methods which focus on extracting effective features with the random sampling strategy, we develop a deep reinforcement learning method to select samples which are more suitable for learning discriminative features, so that the overall performance can be improved. Specifically, our method uses two subnetworks to achieve the kinship verification task: one DQN-based sampling network to filter the negative samples, and one multi-layer convolutional network to verify the kin relationship. Experimental results on the KinFaceW-I and KinFaceW-II datasets show the superiority of our proposed approach over the state-of-the-arts.

在本文中，我们提出了一种判别抽样方法，通过深度强化学习选择最有效的阴性样本进行亲缘关系验证。与大多数现有的面部亲缘关系验证方法专注于通过随机采样策略提取有效特征不同，我们开发了一种深度强化学习方法来选择更适合于学习区分特征的样本，从而可以改善整体性能。具体来说，我们的方法使用两个子网来实现亲属关系验证任务：一个基于DQN的采样网络过滤否定样本，以及一个多层卷积网络来验证亲属关系。KinFaceW-I和KinFaceW-II数据集上的实验结果表明，我们提出的方法优于最新技术。