Abstract
Crowd counting is gaining societal relevance, particularly in domains of Urban Planning, Crowd Management, and Public Safety. This paper introduces Fourier-guided attention (FGA), a novel attention mechanism for crowd count estimation designed to address the inefficient full-scale global pattern capture in existing works on convolution-based attention networks. FGA efficiently captures multi-scale information, including full-scale global patterns, by utilizing Fast-Fourier Transformations (FFT) along with spatial attention for global features and convolutions with channel-wise attention for semi-global and local features. The architecture of FGA involves a dual-path approach: (1) a path for processing full-scale global features through FFT, allowing for efficient extraction of information in the frequency domain, and (2) a path for processing remaining feature maps for semi-global and local features using traditional convolutions and channel-wise attention. This dual-path architecture enables FGA to seamlessly integrate frequency and spatial information, enhancing its ability to capture diverse crowd patterns. We apply FGA in the last layers of two popular crowd-counting works, CSRNet and CANNet, to evaluate the module's performance on benchmark datasets such as ShanghaiTech-A, ShanghaiTech-B, UCF-CC-50, and JHU++ crowd. The experiments demonstrate a notable improvement across all datasets based on Mean-Squared-Error (MSE) and Mean-Absolute-Error (MAE) metrics, showing comparable performance to recent state-of-the-art methods. Additionally, we illustrate the interpretability using qualitative analysis, leveraging Grad-CAM heatmaps, to show the effectiveness of FGA in capturing crowd patterns.
Abstract (translated)
人群计数在社会意义上有越来越多的重要性，特别是在城市规划、人群管理和公共安全等领域。本文介绍了一种名为Fourier引导关注（FGA）的新 crowd count 估计注意力机制，旨在解决现有基于卷积基注意网络的工作中的全局模式捕捉效率低下的问题。FGA 通过利用 Fast-Fourier Transforms（FFT）和空间注意力来捕捉多尺度信息，包括全局模式，从而有效地提取频率域中的信息。此外，FGA 使用传统的卷积和通道级注意力来处理剩余的半全局和局部特征。这种双路径架构使得FGA 可以轻松整合频率和空间信息，提高其捕捉多样 crowd 模式的能力。我们在两个流行的 crowd-counting 作品中应用 FGA，分别是 CSRNet 和 CANNet，以评估其在基准数据集（如上海Tech-A、上海Tech-B、UCF-CC-50 和 JHU+）上的性能。实验结果表明，所有数据集基于平均平方误差（MSE）和平均绝对误差（MAE）的评估结果都有显著的改进，显示出与最近最先进的方法的性能相当。此外，我们通过使用 Grad-CAM 热图进行定性分析，展示了 FGA 在捕捉 crowd patterns 中的有效性。
URL
https://arxiv.org/abs/2407.06110
