论文标题
级联回归跟踪：朝在线硬干扰歧视
Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
论文作者
论文摘要
相似的周围物体可以轻松打扰视觉跟踪。尽管是负面样本中的少数群体，但诸如硬干扰器之类的对象增加了目标漂移和模型腐败的风险，这在在线跟踪和模型更新中应受到更多关注。为了增强跟踪鲁棒性，在本文中，我们提出了一个具有两个顺序阶段的级联回归跟踪器。在第一阶段，我们通过有效的卷积回归来滤除丰富的易于识别的负面候选者。在第二阶段，基于离散抽样的脊回归旨在仔细检查剩余的模棱两可的硬样品，该样本可替代完全连接的层，并从封闭形式的求解器中受益，以进行有效的学习。在11个挑战性的跟踪基准上进行了广泛的实验，包括OTB-2013，OTB-2015，Dot2018，dot2019，UAV123，Temple-Color，NFS，NFS，Trackingnet，Lasot，Lasot，UAV20L和Oxuva。提出的方法在实时速度下运行时，在普遍的基准测试中实现了最先进的性能。
Visual tracking can be easily disturbed by similar surrounding objects. Such objects as hard distractors, even though being the minority among negative samples, increase the risk of target drift and model corruption, which deserve additional attention in online tracking and model update. To enhance the tracking robustness, in this paper, we propose a cascaded regression tracker with two sequential stages. In the first stage, we filter out abundant easily-identified negative candidates via an efficient convolutional regression. In the second stage, a discrete sampling based ridge regression is designed to double-check the remaining ambiguous hard samples, which serves as an alternative of fully-connected layers and benefits from the closed-form solver for efficient learning. Extensive experiments are conducted on 11 challenging tracking benchmarks including OTB-2013, OTB-2015, VOT2018, VOT2019, UAV123, Temple-Color, NfS, TrackingNet, LaSOT, UAV20L, and OxUvA. The proposed method achieves state-of-the-art performance on prevalent benchmarks, while running in a real-time speed.
