Dynamic Transfer for Domain Adaptation in Crowd Counting

Abstract

We consider the problem of domain adaptation in crowd counting. Given a pre-trained model learned from a source domain, our goal is to adapt this model to a target domain using unlabeled data. The solution to this problem has a lot of potential applications in computer vision research that require a neural network model adapted to a target dataset. In this paper, we illustrate a dynamic domain adaptation technique. Specifically, we apply dynamic transfer for solving domain adaptation problems in crowd counting. The key insight is that adapting the model for the target domain is achieved by adapting the model across the data samples. The experimental results on several benchmark datasets demonstrate the effectiveness of our approaches.