Adaptive Aggregation of Arbitrary Online Trackers with a Regret Bound
Adaptive Aggregation of Arbitrary Online Trackers with a Regret Bound
复制标题
DOI：
10.1109/wacv45572.2020.9093613
复制
发表时间：
2020-03
期刊：
影响因子：
--
通讯作者：
Heon Song;D. Suehiro;S. Uchida
中科院分区：
文献类型：
--
作者：
Heon Song;D. Suehiro;S. Uchida
我们提出了一种在线的视觉对象跟踪方法，即使在敌对的环境中，各种干扰可能会发生在目标外观等，该方法是基于延迟对冲算法聚合多个任意的在线跟踪器与自适应权重的鲁棒性。利用延迟对冲算法的性质，从理论上保证了跟踪性能的鲁棒性。粗略地说，所提出的方法可以实现类似的跟踪性能的最好的一个在所有的跟踪器被聚合在一个对抗性的环境。对不同跟踪任务的实验研究表明，该方法可以通过聚合各种在线跟踪器来实现最先进的性能。
We propose an online visual-object tracking method that is robust even in an adversarial environment, where various disturbances may occur on the target appearance, etc. The proposed method is based on a delayed-Hedge algorithm for aggregating multiple arbitrary online trackers with adaptive weights. The robustness in the tracking performance is guaranteed theoretically in term of "regret" by the property of the delayed-Hedge algorithm. Roughly speaking, the proposed method can achieve a similar tracking performance as the best one among all the trackers to be aggregated in an adversarial environment. The experimental study on various tracking tasks shows that the proposed method could achieve state-of-the-art performance by aggregating various online trackers.