The rapid development and popularization of video surveillance highlight the critical and challenging problem, vehicle reidentification, which suffers from the limited interinstance discrepancy between different vehicle identities and large intrainstance differences of the same vehicle. In this article, we propose a novel multilevel attention network to hierarchically learn an efficient feature embedding for vehicle re-ID. Three kinds of attention are designed in the network: hard local-level attention to localize vehicle salient parts, soft pixel-level attention to refine attended pixels both globally and locally, and spatial attention to enhance the encoder’s spatial awareness of salient regions within the windscreen area. Multigrain features are subsequently learned from semantic awareness to spatial awareness, guaranteeing the intraclass compactness and interclass separability for vehicle re-ID. Extensive experiments validate the effectiveness of each attention component and demonstrate that our approach outperforms the state-of-the-art re-ID methods on two challenging datasets: VehicleID and Vehicle-1 M.

中文翻译：

---

从语义到空间意识：具有多重注意力机制的车辆重新识别

视频监控的快速发展和普及凸显了车辆重新识别的关键和挑战性问题，该问题受到不同车辆身份之间的实例间差异有限和同一车辆的较大内部差异的影响。在本文中，我们提出了一种新颖的多级注意力网络，以分层学习车辆 re-ID 的有效特征嵌入。网络中设计了三种注意力：用于定位车辆显着部分的硬局部注意力，用于全局和局部细化参与像素的软像素级注意力，以及用于增强编码器对挡风玻璃内显着区域的空间意识的空间注意力区域。多粒特征随后从语义意识学习到空间意识，保证车辆 re-ID 的类内紧凑性和类间可分离性。大量实验验证了每个注意力组件的有效性，并证明我们的方法在两个具有挑战性的数据集上优于最先进的 re-ID 方法：VehicleID 和 Vehicle-1 M。