.png){kind=icon}
.png){kind=icon}
Return
Fourier transform-based single domain generalization for crowd counting
.png){kind=icon}
OA
AI
DOI：10.1038/s41598-026-46286-3.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Accurate crowd counting is critical for numerous real-world applications. However, domain shift poses a significant barrier to deploying crowd counting models in practical scenarios due to the discrepancy between training and target domains. This paper proposes SinCount, a novel crowd counting framework designed for the Single-source Domain Generalization (SDG) setting, capable of generalizing to unseen domains. SinCount introduces a task-frequency alignment mechanism, directing high-frequency cues toward fine-grained density regression while allocating low-frequency cues to region-level classification to mitigate domain shift. Specifically, we develop a frequency-specific feature extraction module to extract high-frequency and low-frequency features. Subsequently, a dual-attention strategy is devised to embed high-frequency features via spatial attention for the regression branch, while modulating low-frequency features via channel attention for the classification branch. Moreover, an instance normalization mask and an attention consistency loss are incorporated to suppress domain-specific noise and stabilize feature learning. Evaluations across multiple benchmark datasets demonstrate that our method achieves competitive performance compared to state-of-the-art SDG approaches. The code is publicly available at https://github.com/Twiwq/SinCount.
Keywords:
Computational biology and bioinformatics
Mathematics and computing
Single domain generalization
Fast fourier transformation
Crowd counting
Density map estimation
Frequency-aware attention
Science
Humanities and Social Sciences
multidisciplinary
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.