Multi-Granularity Distribution Alignment for Cross-Domain Crowd Counting
IEEE Transactions on Image Processing · 2025 · 34 · 3648-3662
DOI: 10.1109/tip.2025.3571312 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Xian Zhong und 5 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 60 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Hubei Provincial Key Research and Development Program.
Abstract (Originalsprache)
Unsupervised domain adaptation enables the transfer of knowledge from a labeled source domain to an unlabeled target domain, and its application in crowd counting is gaining momentum. Current methods typically align distributions across domains to address inter-domain disparities at a global level. However, these methods often struggle with significant intra-domain gaps caused by domain-agnostic factors such as density, surveillance angles, and scale, leading to inaccurate alignment and unnecessary computational burdens, especially in large-scale training scenarios. To address these challenges, we propose the Multi-Granularity Optimal Transport (MGOT) distribution alignment framework, which aligns domain-agnostic factors across domains at different granularities. The motivation behind multi-granularity is to capture fine-grained domain-agnostic variations within domains. Our method proceeds in three phases: first, clustering coarse-grained features based on intra-domain similarity; second, aligning the granular clusters using an optimal transport framework and constructing a mapping from cluster centers to finer patch levels between domains; and third, re-weighting the aligned distribution for model refinement in domain adaptation. Extensive experiments across twelve cross-domain benchmarks show that our method outperforms existing state-of-the-art methods in adaptive crowd counting. The code will be available at https://github.com/HopooLinZ/MGOT.
Förderung
- National Natural Science Foundation of China
- Hubei Provincial Key Research and Development Program
Zitieren
APA
Zhong, X., Qiu, L., Zhu, H., Yuan, J., He, S., & Wang, Z. (2025). Multi-Granularity Distribution Alignment for Cross-Domain Crowd Counting. IEEE Transactions on Image Processing, 34, 3648-3662. https://doi.org/10.1109/tip.2025.3571312
Vancouver
Zhong X, Qiu L, Zhu H, Yuan J, He S, Wang Z. Multi-Granularity Distribution Alignment for Cross-Domain Crowd Counting. IEEE Transactions on Image Processing. 2025;34:3648-3662. doi:10.1109/tip.2025.3571312
BibTeX
@article{Zhong2025,
author = {Zhong, Xian and Qiu, Lingyue and Zhu, Huilin and Yuan, Jingling and He, Shengfeng and Wang, Zheng},
title = {Multi-Granularity Distribution Alignment for Cross-Domain Crowd Counting},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {3648--3662},
doi = {10.1109/tip.2025.3571312}
}
EUVIMED