跳到主要导航 跳到搜索 跳到主要内容

Cross-alignment for efficient visual object tracking

  • Shilei Wang
  • , Mingjiang Liang
  • , Shaoli Huang
  • , Jifeng Ning
  • , Gong Cheng
  • Northwest Agriculture and Forestry University
  • Northwestern Polytechnical University Xian
  • University of Technology Sydney
  • Tencent

科研成果: 期刊稿件 › 文章 › 同行评审

10 引用 (Scopus)

摘要

In visual object tracking, the disparity in performance between lightweight and heavyweight trackers presents a significant challenge, particularly for applications on edge devices. We introduce the Cross-Alignment Tracker (CAT), a novel dual-branch framework designed to bridge the performance gap by integrating both lightweight and heavyweight tracking components. During training, CAT processes inputs through two parallel branches, each consisting of a backbone network and a tracking head—one lightweight and the other heavyweight. This design facilitates simultaneous learning and output alignment across branches, thereby enhancing the performance of the lightweight tracker in a coordinated manner. A key aspect of our approach is the adaptation and alignment of outputs from both branches, ensuring that the accuracy and robustness of the heavyweight tracker can effectively guide and improve the learning of its lightweight counterpart. During online tracking, CAT leverages cross-combinations between the two branches to simultaneously generate four distinct one-stream trackers, each with varying levels of computational complexity and parameter size. Empirical evaluations, notably on the GOT-10k benchmark, reveal that CAT-Tiny surpasses existing real-time trackers by 4.8%, approaching the prowess of larger, high-performance models. Remarkably, a single training session yields four distinct model sizes, each tailored for varied tracking demands, showcasing the method's unparalleled efficiency and scalability in advancing real-time object-tracking technology.

源语言英语
期刊论文编号112048
期刊Pattern Recognition
卷170
DOI
出版状态已出版 - 2月 2026

学术指纹

探究 'Cross-alignment for efficient visual object tracking' 的科研主题。它们共同构成独一无二的学术指纹。

引用此