AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting

We address the problem of image-based crowd counting. In particular, we propose a new problem called unlabeled scene-adaptive crowd counting. Given a new target scene, we would like to have a crowd counting model specifically adapted to this particular scene based on the target data that capture some information about the new scene. In this paper, we propose to use one or more unlabeled images from the target scene to perform the adaptation. In comparison with the existing problem setups (e.g. fully supervised), our proposed problem setup is closer to the real-world applications of crowd counting systems. We introduce a novel AdaCrowd framework to solve this problem. Our framework consists of a crowd counting network and a guiding network. The guiding network predicts some parameters in the crowd counting network based on the unlabeled images from a particular scene. This allows our model to adapt to different target scenes. The experimental results on several challenging benchmark datasets demonstrate the effectiveness of our proposed approach compared with other alternative methods. Code is available at https://github.com/maheshkkumar/adacrowd

Automated summary

This paper addresses the problem of image-based crowd counting and proposes a new problem setup called unlabeled scene-adaptive crowd counting. By using unlabeled images from the target scene, the proposed problem setup aims to adapt the crowd counting model to specific scenes. The authors introduce the AdaCrowd framework, which consists of a crowd counting network and a guiding network, and demonstrate its effectiveness through experimental results.