论文标题
语义引导部分注意网络的方向感知车辆重新识别
Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network
论文作者
论文摘要
车辆重新识别（RE-ID）着重于跨不同摄像头匹配同一车辆的图像。这在根本上是具有挑战性的，因为车辆之间的差异有时是微妙的。虽然几项研究结合了空间注意机制来帮助车辆重新使用，但如果不接受昂贵的标签训练，它们通常需要昂贵的键盘标签或遇到嘈杂的注意面罩。在这项工作中，我们提出了一个专用的语义引导的部分注意网络（SPAN），以稳健地预测训练过程中仅给出图像级语义标签的车辆不同视图的部分注意力掩模。借助零件注意面罩，我们可以在每个部分中分别提取区分特征。然后，我们介绍共发生的零件距离距离度量（CPDM），该指标（CPDM）在评估两个图像的特征距离时更加强调同时车辆零件。广泛的实验验证了所提出的方法的有效性，并表明我们的框架的表现优于最先进的方法。
Vehicle re-identification (re-ID) focuses on matching images of the same vehicle across different cameras. It is fundamentally challenging because differences between vehicles are sometimes subtle. While several studies incorporate spatial-attention mechanisms to help vehicle re-ID, they often require expensive keypoint labels or suffer from noisy attention mask if not trained with expensive labels. In this work, we propose a dedicated Semantics-guided Part Attention Network (SPAN) to robustly predict part attention masks for different views of vehicles given only image-level semantic labels during training. With the help of part attention masks, we can extract discriminative features in each part separately. Then we introduce Co-occurrence Part-attentive Distance Metric (CPDM) which places greater emphasis on co-occurrence vehicle parts when evaluating the feature distance of two images. Extensive experiments validate the effectiveness of the proposed method and show that our framework outperforms the state-of-the-art approaches.
