论文标题
与自行车一致的暹罗网络的自我监督对象跟踪
Self-supervised Object Tracking with Cycle-consistent Siamese Networks
论文作者
论文摘要
与监督的学习相比，视觉对象跟踪的自学学习具有宝贵的优势，例如不必要的人类注释和在线培训。在这项工作中，我们在一个循环一致的自我监视框架中利用端到端的暹罗网络进行对象跟踪。可以通过利用向前和向后跟踪中的周期一致性来执行自我判断。为了更好地利用深层网络的端到端学习，我们建议在我们的跟踪框架中整合暹罗地区建议和掩盖回归网络，以便可以在没有每个框架注释的情况下学习快速，更准确的跟踪器。用于视觉对象跟踪和戴维斯数据集的“视频对象分割传播的戴维斯数据集”的实验表明，我们的方法在这两个任务上都超过了先验方法。
Self-supervised learning for visual object tracking possesses valuable advantages compared to supervised learning, such as the non-necessity of laborious human annotations and online training. In this work, we exploit an end-to-end Siamese network in a cycle-consistent self-supervised framework for object tracking. Self-supervision can be performed by taking advantage of the cycle consistency in the forward and backward tracking. To better leverage the end-to-end learning of deep networks, we propose to integrate a Siamese region proposal and mask regression network in our tracking framework so that a fast and more accurate tracker can be learned without the annotation of each frame. The experiments on the VOT dataset for visual object tracking and on the DAVIS dataset for video object segmentation propagation show that our method outperforms prior approaches on both tasks.
