论文标题
通过分层量表重新校准网络计数的人群计数
Crowd Counting via Hierarchical Scale Recalibration Network
论文作者
论文摘要
由于困难，尤其是视力量表的巨大差异，人群计数的任务极具挑战性。以前的工作倾向于采用多尺度信息的幼稚串联来解决该信息，而在特征图之间的比例位置则被忽略。在本文中，我们提出了一个新颖的分层量表重新校准网络（HSRNET），该网络通过对丰富的上下文依赖性进行建模并重新校准多个尺度相关信息来解决上述问题。具体而言，量表焦点模块（SFM）首先通过依次沿通道和空间维度建模语义相互依赖性，将全局上下文整合到本地特征中。为了重新分配通道特征响应，刻度重新校准模块（SRM）采用逐步融合来生成最终密度图。此外，我们提出了一种新型的量表一致性损失，以限制与规模相关的输出与不同尺度的地面图相一致的。借助提出的模块，我们的方法可以选择性地忽略各种噪音，并自动专注于适当的人群量表。关于人群计数数据集（Shanghaitech，Mall，WorldExpo'10和UCSD）的广泛实验表明，我们的HSRNET可以比所有最新方法都能提供卓越的结果。更明显的是，我们扩展了额外的车辆数据集的实验，其结果表明该模型已推广到其他应用程序。
The task of crowd counting is extremely challenging due to complicated difficulties, especially the huge variation in vision scale. Previous works tend to adopt a naive concatenation of multi-scale information to tackle it, while the scale shifts between the feature maps are ignored. In this paper, we propose a novel Hierarchical Scale Recalibration Network (HSRNet), which addresses the above issues by modeling rich contextual dependencies and recalibrating multiple scale-associated information. Specifically, a Scale Focus Module (SFM) first integrates global context into local features by modeling the semantic inter-dependencies along channel and spatial dimensions sequentially. In order to reallocate channel-wise feature responses, a Scale Recalibration Module (SRM) adopts a step-by-step fusion to generate final density maps. Furthermore, we propose a novel Scale Consistency loss to constrain that the scale-associated outputs are coherent with groundtruth of different scales. With the proposed modules, our approach can ignore various noises selectively and focus on appropriate crowd scales automatically. Extensive experiments on crowd counting datasets (ShanghaiTech, MALL, WorldEXPO'10, and UCSD) show that our HSRNet can deliver superior results over all state-of-the-art approaches. More remarkably, we extend experiments on an extra vehicle dataset, whose results indicate that the proposed model is generalized to other applications.
