用于尺度不变群体计数的层间和层内尺度聚集
Interlayer and Intralayer Scale Aggregation for Scale-invariant Crowd Counting
摘要：
人群计数是一项重要的视觉任务，它面临着给定场景内连续尺度变化和图像内和图像间巨大密度变化的挑战。这些挑战通常在现有方法中使用多柱结构来解决。然而，由于捕获多尺度特征的能力有限、对大密度偏移的敏感性以及训练多分支模型的困难，这种方法不能提供一致的改进和可移植性。为了克服这些局限性，本文提出了一种单列尺度不变网络（ScSiNet），它通过层间多尺度积分和一种新的层内尺度不变变换（SiT）相结合来提取复杂的尺度不变特征。此外，为了扩大密度的多样性，提出了一种随机积分损失来训练我们的单分支方法。在公开数据集上的大量实验表明，该方法在计数精度上始终优于现有方法，并具有显著的可移植性和尺度不变性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
