Offline Siamese networks have achieved very promising tracking performance, especially in accuracy and efficiency. However, they often fail to track an object in complex scenes due to the incapacity in online update. Traditional updaters are difficult to process the irregular variations and sampling noises of objects, so it is quite risky to adopt them to update Siamese networks. In this paper, we first present a two-stage one-shot learner, which can predict the local parameters of primary classifier with object samples from diverse stages. Then, an updatable Siamese network is proposed based on the learner (SiamTOL), which is able to complement online update by itself. Concretely, we introduce an extra inputting branch to sequentially capture the latest object features, and design a residual module to update the initial exemplar using these features. Besides, an effective multi-aspect training loss is designed for our network to avoid overfit. Extensive experimental results on several popular benchmarks including OTB100, VOT2018, VOT2019, LaSOT, UAV123 and GOT10k manifest that the proposed tracker achieves the leading performance and outperforms other state-of-the-art methods
翻译:离线的暹粒网络取得了非常有希望的追踪性能,特别是在准确性和效率方面。然而,由于无法在线更新,它们往往无法在复杂的场景中追踪一个物体。传统的更新器很难处理物体的异常变化和取样噪音,因此采用它们更新暹粒网络非常危险。在本文中,我们首先提出一个两阶段一发学习器,可以预测初级分类器的本地参数,并有不同阶段的物体样本。然后,根据学习器(SiamTOL),提出一个升级的Siamese网络,该学习器能够自行补充在线更新。具体地说,我们引入一个额外的输入分支,以便按顺序捕捉最新的物体特征,并设计一个剩余模块,利用这些特征更新最初的外观。此外,为我们的网络设计了一个有效的多层培训损失,以避免过度使用。在几个流行基准上取得了广泛的实验结果,包括OTB100、VOT2018、VOT2019、LSOT、UAAV123和GOT10k 显示, 拟议的跟踪器能够实现主要性表现和超出其他状态的方法。