Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
7-2023
Abstract
Due to domain shift, a large performance drop is usually observed when a trained crowd counting model is deployed in the wild. While existing domain-adaptive crowd counting methods achieve promising results, they typically regard each crowd image as a whole and reduce domain discrepancies in a holistic manner, thus limiting further improvement of domain adaptation performance. To this end, we propose to untangle domain-invariant crowd and domain-specific background from crowd images and design a fine-grained domain adaption method for crowd counting. Specifically, to disentangle crowd from background, we propose to learn crowd segmentation from point-level crowd counting annotations in a weakly-supervised manner. Based on the derived segmentation, we design a crowd-aware domain adaptation mechanism consisting of two crowd-aware adaptation modules, i.e., Crowd Region Transfer (CRT) and Crowd Density Alignment (CDA). The CRT module is designed to guide crowd features transfer across domains beyond background distractions. The CDA module dedicates to regularising target-domain crowd density generation by its own crowd density distribution. Our method outperforms previous approaches consistently in the widely-used adaptation scenarios.
Keywords
Crowd counting, Domain adaptation, Pointderived segmentation, Computer vision
Discipline
Artificial Intelligence and Robotics | Graphics and Human Computer Interfaces
Research Areas
Software and Cyber-Physical Systems
Publication
Proceedings of 2023 IEEE International Conference on Multimedia and Expo (ICME), Brisbane, Australia, July 10-14
First Page
2363
Last Page
2368
ISBN
9781665468923
Identifier
10.1109/ICME55011.2023.00403
Publisher
IEEE Computer Society
City or Country
New York, NY, USA
Citation
LIU, Yongtuo; XU, Dan; REN, Sucheng; WU, Hanjie; CAI, Hongmin; and HE, Shengfeng.
Fine-grained domain adaptive crowd counting via point-derived segmentation. (2023). Proceedings of 2023 IEEE International Conference on Multimedia and Expo (ICME), Brisbane, Australia, July 10-14. 2363-2368.
Available at: https://ink.library.smu.edu.sg/sis_research/8443
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/ICME55011.2023.00403
Included in
Artificial Intelligence and Robotics Commons, Graphics and Human Computer Interfaces Commons