Deep regression trackers are among the fastest tracking algorithms available, and therefore suitable for real-time robotic applications. However, their accuracy is inadequate in many domains due to distribution shift and overfitting. In this letter we overcome such limitations by presenting the first methodology for domain adaption of such a class of trackers. To reduce the labeling effort we propose a weakly-supervised adaptation strategy, in which reinforcement learning is used to express weak supervision as a scalar application-dependent and temporally-delayed feedback. At the same time, knowledge distillation is employed to guarantee learning stability and to compress and transfer knowledge from more powerful but slower trackers. Extensive experiments on five different robotic vision domains demonstrate the relevance of our methodology. Real-time speed is achieved on embedded devices and on machines without GPUs, while accuracy reaches significant results.

中文翻译：

---

通过强化知识蒸馏的深度回归跟踪器的弱监督域适应


深度回归跟踪器是可用的最快跟踪算法之一，因此适合实时机器人应用。然而，由于分布偏移和过度拟合，它们的准确性在许多领域都不够。在这封信中，我们通过提出此类跟踪器的域适应的第一种方法来克服这些限制。为了减少标记工作，我们提出了一种弱监督适应策略，其中强化学习用于将弱监督表示为依赖于标量应用程序和时间延迟的反馈。同时，采用知识蒸馏来保证学习稳定性，并压缩和传输来自更强大但更慢的跟踪器的知识。对五个不同机器人视觉领域的广泛实验证明了我们方法的相关性。在嵌入式设备和没有 GPU 的机器上实现了实时速度，同时精度也达到了显着的效果。