论文标题
Skelevision：通过多任务学习对人跟踪的对抗性弹性
SkeleVision: Towards Adversarial Resiliency of Person Tracking with Multi-Task Learning
论文作者
论文摘要
使用计算机视觉技术的人员跟踪具有广泛的应用程序，例如自动驾驶，家庭安全和体育分析。但是，对抗性攻击的威胁日益增长，引起了人们对此类技术的安全性和可靠性的严重关注。在这项工作中，我们研究了在人跟踪的背景下，多任务学习（MTL）对广泛使用的siamrpn跟踪器的对抗性鲁棒性的影响。具体而言，我们研究了人跟踪和人类关键点检测的语义类似任务共同学习的效果。我们通过更强大的对抗性攻击进行了广泛的实验，这些攻击可以在物理上可以实现，这表明了我们方法的实际价值。我们对模拟以及现实世界数据集的实证研究表明，与通常仅在人跟踪的单个任务上进行培训相比，使用MTL的培训始终使攻击SiamRPN跟踪器变得更加困难。
Person tracking using computer vision techniques has wide ranging applications such as autonomous driving, home security and sports analytics. However, the growing threat of adversarial attacks raises serious concerns regarding the security and reliability of such techniques. In this work, we study the impact of multi-task learning (MTL) on the adversarial robustness of the widely used SiamRPN tracker, in the context of person tracking. Specifically, we investigate the effect of jointly learning with semantically analogous tasks of person tracking and human keypoint detection. We conduct extensive experiments with more powerful adversarial attacks that can be physically realizable, demonstrating the practical value of our approach. Our empirical study with simulated as well as real-world datasets reveals that training with MTL consistently makes it harder to attack the SiamRPN tracker, compared to typically training only on the single task of person tracking.
