AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
This addresses the challenge of deploying crowd counting systems in real-world scenarios where labeled data is scarce, though it is incremental as it builds on existing adaptation methods.
The paper tackles the problem of adapting crowd counting models to new scenes using only unlabeled images, proposing the AdaCrowd framework which uses a guiding network to adjust parameters based on scene-specific data, and shows effectiveness on benchmark datasets.
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.