DAOT: Domain-Agnostically Aligned Optimal Transport for domain-adaptive crowd counting

• Main Authors: ZHU, Huilin, YUAN, Jingling, ZHONG, Xian, YANG, Zhengwei, WANG, Zheng, HE, Shengfeng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Crowd counting; Domain adaptation; Domain-agnostic alignment; Optimal transport; HTTP; Graphics and Human Computer Interfaces; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/8423; https://ink.library.smu.edu.sg/context/sis_research/article/9426/viewcontent/2308.05311.pdf
• Institution: Singapore Management University

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/.