用零膨胀泊松模型解决人群计数中稀疏标注与数据分布不匹配问题。
ZIP: Scalable Crowd Counting via Zero-Inflated Poisson Modeling
- 采用零膨胀泊松模型，分别建模空块概率和实际人数分布。
- 在多个数据集上优于现有方法，尤其在大模型下性能更优。
- 适合需要高精度人群计数的场景，如安防监控与城市规划。
现有人群计数方法多使用均方误差（MSE）直接回归块级密度图，存在两大缺陷：(1) 忽视标注极度稀疏——标准基准中超过95%的8×8区块为空，导致有效区域的监督信号被大量零值稀释；(2) MSE对应高斯误差模型，难以匹配离散、非负的计数数据。为此，我们提出ZIP框架，以零膨胀泊松似然建模块级人数：零膨胀项学习区块结构为空的概率（处理过量零值），泊松分量则捕捉有人时的期望数量（尊重离散性）。我们提供泛化分析，证明当训练分辨率适中时，ZIP的风险界优于MSE与DMCount。为验证可扩展性，我们在参数量与计算量相差超100倍的骨干网络上实现ZIP。在ShanghaiTech A & B、UCF-QNRF、NWPU-Crowd上的实验表明，ZIP在所有模型规模下均持续超越当前最优方法。
原文摘要 · Abstract (English)
Most crowd counting methods directly regress blockwise density maps using Mean Squared Error (MSE) losses. This practice has two key limitations: (1) it fails to account for the extreme spatial sparsity of annotations - over 95% of 8x8 blocks are empty across standard benchmarks, so supervision signals in informative regions are diluted by the predominant zeros; (2) MSE corresponds to a Gaussian error model that poorly matches discrete, non-negative count data. To address these issues, we introduce ZIP, a scalable crowd counting framework that models blockwise counts with a Zero-Inflated Poisson likelihood: a zero-inflation term learns the probability a block is structurally empty (handling excess zeros), while the Poisson component captures expected counts when people are present (respecting discreteness). We provide a generalization analysis showing a tighter risk bound for ZIP than MSE-based losses and DMCount provided that the training resolution is moderately large. To assess the scalability of ZIP, we instantiate it on backbones spanning over 100x in parameters/compute. Experiments on ShanghaiTech A & B, UCF-QNRF, and NWPU-Crowd demonstrate that ZIP consistently surpasses state-of-the-art methods across all model scales.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。