论文标题
裂缝：级联回归 - 排列分类，用于可靠的视觉跟踪
CRACT: Cascaded Regression-Align-Classification for Robust Visual Tracking
论文作者
论文摘要
高质量的对象建议在使用区域建议网络（RPN）的视觉跟踪算法中至关重要。通常通过盒子回归和并行分类的这些提案的细化已被普遍采用，以提高跟踪性能。但是，在处理复杂而动态的背景时，它仍然会遇到问题。因此，在本文中，我们引入了改进的提案完善模块，级联回归 - 分类（CRAC），该模块在许多基准上产生了新的最新性能。 首先，在观察到盒子回归的偏移可以作为提案功能改进的指导之后，我们将CRAC设计为一系列盒子回归，功能对齐和盒子分类。关键是通过对齐步骤桥接盒子的回归和分类，这为提案分类提供了更准确的特征，并提高了鲁棒性。为了解决对象外观的变化，我们引入了用于盒子分类的标识歧视组件，该组件利用了离线可靠的细粒模板和在线丰富的背景信息，以将目标与背景区分开。此外，我们提出了金字塔皇家，该金字塔通过利用建议的本地和全球提示来使CRAC受益。在推论期间，通过对所有精致的建议进行排名并选择最佳提案来跟踪收益。在包括OTB-2015，UAV123，NFS，FOT-2018，TrackingNet，GoT-10k和Lasot在内的七个基准测试的实验中，与最先进的竞争对手和实时跑步相比，我们的裂缝表现出非常有希望的结果。
High quality object proposals are crucial in visual tracking algorithms that utilize region proposal network (RPN). Refinement of these proposals, typically by box regression and classification in parallel, has been popularly adopted to boost tracking performance. However, it still meets problems when dealing with complex and dynamic background. Thus motivated, in this paper we introduce an improved proposal refinement module, Cascaded Regression-Align-Classification (CRAC), which yields new state-of-the-art performances on many benchmarks. First, having observed that the offsets from box regression can serve as guidance for proposal feature refinement, we design CRAC as a cascade of box regression, feature alignment and box classification. The key is to bridge box regression and classification via an alignment step, which leads to more accurate features for proposal classification with improved robustness. To address the variation in object appearance, we introduce an identification-discrimination component for box classification, which leverages offline reliable fine-grained template and online rich background information to distinguish the target from background. Moreover, we present pyramid RoIAlign that benefits CRAC by exploiting both the local and global cues of proposals. During inference, tracking proceeds by ranking all refined proposals and selecting the best one. In experiments on seven benchmarks including OTB-2015, UAV123, NfS, VOT-2018, TrackingNet, GOT-10k and LaSOT, our CRACT exhibits very promising results in comparison with state-of-the-art competitors and runs in real-time.
