Self-aware circular response-guided attention for robust siamese tracking
Self-aware circular response-guided attention for robust siamese tracking
复制标题
DOI：
10.1007/s10489-022-04314-5
复制
发表时间：
2022-12
影响因子：
5.3
通讯作者：
Huibin Tan;Mengzhu Wang;Tianyi Liang;Liyang Xu;Yuhua Tang;Long Lan;Wenjing Yang
中科院分区：
文献类型：
--
作者：
Huibin Tan;Mengzhu Wang;Tianyi Liang;Liyang Xu;Yuhua Tang;Long Lan;Wenjing Yang
暹罗跟踪器最近在准确性方面取得了显着的进步，但进一步的改进受到语义干扰。一个潜在的原因可能是缺乏视觉跟踪的先验信息。用于暹罗跟踪器目标定位的最终响应图表示了目标与搜索分支中密集图像块之间的相似性关联，它恰好是一种自然先验信息。本文从如何利用反应图中的隐含信息的角度出发，提出了一种基于自我感知的圆形反应引导注意的连体动物跟踪方法。首先，设计了一个嵌入在Siamese网络中的多级自感知循环框架，融合多级网络特征和先验信息，实现更有效的信息集成。具体地，这些先验信息，即，分别通过密集结构空间注意力模块（DSSA）和自底向上通道注意力模块（BUCA）从多层次响应图中挖掘出多层次空间注意力和多层次通道注意力。此外，DSSA吸收了一致的稀疏约束项，以加强多层次响应图之间的关联。实验表明，我们的SC-Siam和SC-Siam-ResNet跟踪器（以SiamDWFC和Siam-ResNet为基线）在七个基准测试中达到了最先进的性能，包括OTB 2013，OTB 2015，VOT 2016，VOT 2018，VOT 2020，GOT 10 K和LASOT。
Siamese trackers recently have achieved remarkable advancements in accuracy, yet the further improvement is subject to semantic interferences. An potential reason may be the lack of prior information in visual tracking. The final response map used for target location in a Siamese tracker represents the similarity associations between the target and dense image patches in search branch, which happens to be a kind of natural prior information. In this paper, we propose a self-aware circular response-guided attention for Siamese tracking from the angle how to use the implicit information in response maps. Firstly, a multi-level self-aware circular framework embedded in Siamese network is designed to fuse multi-level network features and prior information for more effective information integration. Specifically, these prior information, i.e., multi-level spatial and channel attentions, are exploited from multi-level response maps respectively via densely structured spatial attention module (DSSA) and bottom-up channel attention module (BUCA). Besides, DSSA absorbs a consistent sparse constraint term to strengthen the association of multi-level response maps. The experiments show that our SC-Siam and SC-Siam-ResNet trackers (with SiamDWFC and Siam-ResNet as baselines) achieve state-of-the-art performance on seven benchmarks, including OTB2013, OTB2015, VOT2016, VOT2018, VOT2020, GOT10K, and LASOT.