Discriminative sampling via deep reinforcement learning for kinship verification

Abstract

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.