论文标题
与结构化辍学
Tackling Occlusion in Siamese Tracking with Structured Dropouts
论文作者
论文摘要
闭塞是对象跟踪模型中最困难的挑战之一。这是因为与其他挑战不同，数据增加可能会有所帮助，因此很难模拟阻塞，因为遮挡对象可以是任何形状的任何东西。在本文中，我们提出了一个简单的解决方案，以模拟潜在空间中闭塞的影响。具体而言，我们提出结构化的辍学，以模仿遮挡下潜在代码的变化。我们介绍了三种形式的辍学形式（渠道辍学，段辍学和切片辍学），考虑到各种形式的遮挡形式。为了证明其有效性，将辍学物纳入了两个现代的暹罗跟踪器（SiamFC和SiamRPN ++）中。使用编码网络将多个辍学的输出组合在一起，以获得最终预测。几个跟踪基准测试的实验显示了结构化辍学的好处，而由于它们的简单性仅需要对现有跟踪器模型进行少量更改。
Occlusion is one of the most difficult challenges in object tracking to model. This is because unlike other challenges, where data augmentation can be of help, occlusion is hard to simulate as the occluding object can be anything in any shape. In this paper, we propose a simple solution to simulate the effects of occlusion in the latent space. Specifically, we present structured dropout to mimick the change in latent codes under occlusion. We present three forms of dropout (channel dropout, segment dropout and slice dropout) with the various forms of occlusion in mind. To demonstrate its effectiveness, the dropouts are incorporated into two modern Siamese trackers (SiamFC and SiamRPN++). The outputs from multiple dropouts are combined using an encoder network to obtain the final prediction. Experiments on several tracking benchmarks show the benefits of structured dropouts, while due to their simplicity requiring only small changes to the existing tracker models.
