论文标题
通过多种视图知识蒸馏的强大重新识别
Robust Re-Identification by Multiple Views Knowledge Distillation
论文作者
论文摘要
为了实现重新识别的鲁棒性，标准方法以视频到视频方式利用跟踪信息。但是，这些解决方案面临单图查询的性能下降（例如，图像到视频设置）。最近的工作通过将时间信息从基于视频的网络转移到基于图像的网络来解决这一严重降解。在这项工作中，我们制定了一种培训策略，该策略允许转移出色的知识，这是由描绘目标对象的一系列观点引起的。我们的建议 - 观看知识蒸馏（VKD） - 将这种视觉品种作为教师框架内的监督信号钉住，教师教育一个观察到更少观点的学生。结果，该学生不仅要优于其老师，而且要优于图像到视频的当前最新水平（MARS的6.3％地图，杜克·维迪奥 - 雷德（Duke-Video-Reid）的地图为6.3％，Veri-776的5％）。对人，车辆和动物重新ID的彻底分析 - 从定性和定量的角度研究VKD的性质。代码可在https://github.com/aimagelab/vkd上找到。
To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion. However, these solutions face a large drop in performance for single image queries (e.g., Image-To-Video setting). Recent works address this severe degradation by transferring temporal information from a Video-based network to an Image-based one. In this work, we devise a training strategy that allows the transfer of a superior knowledge, arising from a set of views depicting the target object. Our proposal - Views Knowledge Distillation (VKD) - pins this visual variety as a supervision signal within a teacher-student framework, where the teacher educates a student who observes fewer views. As a result, the student outperforms not only its teacher but also the current state-of-the-art in Image-To-Video by a wide margin (6.3% mAP on MARS, 8.6% on Duke-Video-ReId and 5% on VeRi-776). A thorough analysis - on Person, Vehicle and Animal Re-ID - investigates the properties of VKD from a qualitatively and quantitatively perspective. Code is available at https://github.com/aimagelab/VKD.
