The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled data. In order to reduce the workload of manual annotation and learn to track arbitrary objects, we propose an unsupervised learning method for visual tracking. The motivation of our unsupervised learning is that a robust tracker should be effective in bidirectional tracking. Specifically, the tracker is able to forward localize a target object in successive frames and backtrace to its initial position in the first frame. Based on such a motivation, in the training process, we measure the consistency between forward and backward trajectories to learn a robust tracker from scratch merely using unlabeled videos. We build our framework on a Siamese correlation filter network, and propose a multi-frame validation scheme and a cost-sensitive loss to facilitate unsupervised learning. Without bells and whistles, the proposed unsupervised tracker achieves the baseline accuracy of classic fully supervised trackers while achieving a real-time speed. Furthermore, our unsupervised framework exhibits a potential in leveraging more unlabeled or weakly labeled data to further improve the tracking accuracy.

中文翻译：

---

用于实时跟踪的无监督深度表示学习

深度学习模型不断带来视觉跟踪的进步。通常，监督学习用于使用昂贵的标记数据来训练这些模型。为了减少人工标注的工作量并学习跟踪任意对象，我们提出了一种用于视觉跟踪的无监督学习方法。我们无监督学习的动机是强大的跟踪器应该在双向跟踪中有效。具体来说，跟踪器能够在连续帧中前向定位目标对象，并回溯到其在第一帧中的初始位置。基于这样的动机，在训练过程中，我们测量前向和后向轨迹之间的一致性，以仅使用未标记的视频从头开始学习一个强大的跟踪器。我们在 Siamese 相关过滤器网络上构建我们的框架，并提出了一个多帧验证方案和一个成本敏感的损失来促进无监督学习。没有花里胡哨，所提出的无监督跟踪器实现了经典全监督跟踪器的基线精度，同时实现了实时速度。此外，我们的无监督框架显示出利用更多未标记或弱标记的数据来进一步提高跟踪精度的潜力。