论文标题
层间和内层量表聚合，用于量表不变人群计数
Interlayer and Intralayer Scale Aggregation for Scale-invariant Crowd Counting
论文作者
论文摘要
人群计数是一项重要的视觉任务，它在给定场景内和图像内部和跨图像内的巨大密度变化方面面临着挑战。这些挑战通常使用现有方法中的多列结构来解决。但是，由于能力有限，捕获多尺度功能，对大密度转移的敏感性以及在训练多支球模型方面的难度，这种方法无法提供一致的提高和可传递性。为了克服这些局限性，本文提出了单列尺度不变网络（SCSINET），该网络通过层间多尺度集成和新颖的内部尺度规模不变转换（SIT）来提取复杂的规模不变特征。此外，为了扩大密度的多样性，为训练我们的单分支方法提出了随机整合的损失。公共数据集上的广泛实验表明，该提出的方法在计算准确性和实现出色的可传递性和规模不变属性方面始终优于最先进的方法。
Crowd counting is an important vision task, which faces challenges on continuous scale variation within a given scene and huge density shift both within and across images. These challenges are typically addressed using multi-column structures in existing methods. However, such an approach does not provide consistent improvement and transferability due to limited ability in capturing multi-scale features, sensitiveness to large density shift, and difficulty in training multi-branch models. To overcome these limitations, a Single-column Scale-invariant Network (ScSiNet) is presented in this paper, which extracts sophisticated scale-invariant features via the combination of interlayer multi-scale integration and a novel intralayer scale-invariant transformation (SiT). Furthermore, in order to enlarge the diversity of densities, a randomly integrated loss is presented for training our single-branch method. Extensive experiments on public datasets demonstrate that the proposed method consistently outperforms state-of-the-art approaches in counting accuracy and achieves remarkable transferability and scale-invariant property.
