Publication Type

Conference Proceeding Article

Version

acceptedVersion

Publication Date

11-2022

Abstract

Domain adaptation is commonly employed in crowd counting to bridge the domain gaps between different datasets. However, existing domain adaptation methods tend to focus on inter-dataset differences while overlooking the intra-differences within the same dataset, leading to additional learning ambiguities. These domain-agnostic factors,e.g., density, surveillance perspective, and scale, can cause significant in-domain variations, and the misalignment of these factors across domains can lead to a drop in performance in cross-domain crowd counting. To address this issue, we propose a Domain-agnostically Aligned Optimal Transport (DAOT) strategy that aligns domain-agnostic factors between domains. The DAOT consists of three steps. First, individual-level differences in domain-agnostic factors are measured using structural similarity (SSIM). Second, the optimal transfer (OT) strategy is employed to smooth out these differences and find the optimal domain-to-domain misalignment, with outlier individuals removed via a virtual "dustbin'' column. Third, knowledge is transferred based on the aligned domain-agnostic factors, and the model is retrained for domain adaptation to bridge the gap across domains. We conduct extensive experiments on five standard crowd-counting benchmarks and demonstrate that the proposed method has strong generalizability across diverse datasets. Our code will be available at: https://github.com/HopooLinZ/DAOT/.

Keywords

Crowd counting, Domain adaptation, Domain-agnostic alignment, Optimal transport, HTTP

Discipline

Graphics and Human Computer Interfaces | Numerical Analysis and Scientific Computing

Research Areas

Software and Cyber-Physical Systems

Publication

MM '23: Proceedings of the 31st ACM International Conference on Multimedia, Ottowa, October 29 - November 3

First Page

4319

Last Page

4329

ISBN

979840070108

Identifier

10.1145/3581783.3611793

Publisher

ACM

City or Country

New York

Copyright Owner and License

Authors

Additional URL

https://doi.org/10.1145/3581783.3611793

Share

COinS