Scene adaptive crowd counting
Loading...
Date
2020-04
Authors
Krishna Reddy, Mahesh Kumar
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
We consider the problem of scene adaptive crowd counting. Given a target camera scene, our goal is to adapt a model to this specific scene with only a few labeled/unlabeled images. The solution to this problem has potential applications in numerous real-world scenarios that require deploying a crowd counting model specially adapted to a target camera. In this thesis, we propose two novel methods for scene adaptive crowd counting. First, inspired by the recently introduced learning to learn paradigm in the context of few-shot regime, we aim to learn the parameters of a crowd counting model in a way to facilitate fast adaptation to the target scene. Second, we introduce a new problem called unlabeled scene adaptive crowd counting. More specifically, we propose to use few unlabeled images from the target scene to perform the adaptation. We introduce a novel AdaCrowd framework to solve this problem and it 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 two proposed approaches.
Description
Keywords
Computer Science, Computer Vision, Machine Learning, Deep Learning, Crowd Counting
Citation
Reddy, M. K. K., Hossain, M., Rochan, M., & Wang, Y. (2020). Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning. In The IEEE Winter Conference on Applications of Computer Vision (pp. 2814-2823).