论文标题
STNET：具有多级辅助因子的比例树网络，用于人群计数
STNet: Scale Tree Network with Multi-level Auxiliator for Crowd Counting
论文作者
论文摘要
人群计数仍然是一项具有挑战性的任务，因为尺度差异的存在，密度不一致和复杂背景的存在可能会严重降低计数准确性。为了与根深蒂固的准确性退化问题作斗争，我们提出了一个新颖而强大的网络，称为比例树网络（STNET），以进行准确的人群计数。 STNET由两个关键组成部分组成：一个比例树的多样性增强子和半监督的多级辅助器。具体而言，多样性增强器旨在丰富比例多样性，从而减轻了由于尺度不足而引起的现有方法的局限性。层次分析的粗到五个人群区域采用了一种新颖的树结构。此外，提出了一个简单而有效的多级辅助因子，以帮助在多个级别上利用可普遍的共享特征，从而使更准确的像素背景认知。整体STNET以端到端的方式进行了训练，而无需手动调整主任务和辅助任务之间的减损权重。对四个挑战的人群数据集进行了广泛的实验，证明了该方法的优越性。
Crowd counting remains a challenging task because the presence of drastic scale variation, density inconsistency, and complex background can seriously degrade the counting accuracy. To battle the ingrained issue of accuracy degradation, we propose a novel and powerful network called Scale Tree Network (STNet) for accurate crowd counting. STNet consists of two key components: a Scale-Tree Diversity Enhancer and a Semi-supervised Multi-level Auxiliator. Specifically, the Diversity Enhancer is designed to enrich scale diversity, which alleviates limitations of existing methods caused by insufficient level of scales. A novel tree structure is adopted to hierarchically parse coarse-to-fine crowd regions. Furthermore, a simple yet effective Multi-level Auxiliator is presented to aid in exploiting generalisable shared characteristics at multiple levels, allowing more accurate pixel-wise background cognition. The overall STNet is trained in an end-to-end manner, without the needs for manually tuning loss weights between the main and the auxiliary tasks. Extensive experiments on four challenging crowd datasets demonstrate the superiority of the proposed method.
