论文标题
视觉跟踪中暹罗网络的示例丢失
Exemplar Loss for Siamese Network in Visual Tracking
论文作者
论文摘要
视觉跟踪在感知系统中起着重要的作用，这是智能运输的关键部分。最近，暹罗网络是一个热门话题，可视觉跟踪，以估算移动目标的轨迹，因为它的精确性和简单框架。通常，由逻辑损失和三胞胎损失监督的暹罗跟踪算法，增加了示例模板和正样品之间的内部产物的值，同时用背景样本降低了内部产品的值。但是，没有通过上述损失函数来考虑来自不同示例的干扰因素，这限制了特征模型的歧视。在本文中，提出了与逻辑损失集成的新示例损失，以通过减少示例中的内部产品来增强特征模型的歧视。没有铃铛和哨子，拟议的算法的表现优于通过后勤损失或三胞胎损失监督的方法。数值结果表明，新开发的算法在公共基准中实现了可比的性能。
Visual tracking plays an important role in perception system, which is a crucial part of intelligent transportation. Recently, Siamese network is a hot topic for visual tracking to estimate moving targets' trajectory, due to its superior accuracy and simple framework. In general, Siamese tracking algorithms, supervised by logistic loss and triplet loss, increase the value of inner product between exemplar template and positive sample while reduce the value of inner product with background sample. However, the distractors from different exemplars are not considered by mentioned loss functions, which limit the feature models' discrimination. In this paper, a new exemplar loss integrated with logistic loss is proposed to enhance the feature model's discrimination by reducing inner products among exemplars. Without the bells and whistles, the proposed algorithm outperforms the methods supervised by logistic loss or triplet loss. Numerical results suggest that the newly developed algorithm achieves comparable performance in public benchmarks.
