BitTorrent跟踪器
计算机科学
人工智能
序列(生物学)
帧(网络)
跟踪(教育)
一般化
任务(项目管理)
特征(语言学)
模式识别(心理学)
眼动
变化(天文学)
机器学习
计算机视觉
数学
管理
经济
物理
哲学
数学分析
心理学
生物
电信
遗传学
天体物理学
语言学
教育学
作者
Xingping Dong,Jianbing Shen,Fatih Porikli,Jiebo Luo,Ling Shao
标识
DOI:10.1109/tpami.2022.3230064
摘要
In this paper, we provide an intuitive viewing to simplify the Siamese-based trackers by converting the tracking task to a classification. Under this viewing, we perform an in-depth analysis for them through visual simulations and real tracking examples, and find that the failure cases in some challenging situations can be regarded as the issue of missing decisive samples in offline training. Since the samples in the initial (first) frame contain rich sequence-specific information, we can regard them as the decisive samples to represent the whole sequence. To quickly adapt the base model to new scenes, a compact latent network is presented via fully using these decisive samples. Specifically, we present a statistics-based compact latent feature for fast adjustment by efficiently extracting the sequence-specific information. Furthermore, a new diverse sample mining strategy is designed for training to further improve the discrimination ability of the proposed compact latent network. Finally, a conditional updating strategy is proposed to efficiently update the basic models to handle scene variation during the tracking phase. To evaluate the generalization ability and effectiveness and of our method, we apply it to adjust three classical Siamese-based trackers, namely SiamRPN++, SiamFC, and SiamBAN. Extensive experimental results on six recent datasets demonstrate that all three adjusted trackers obtain the superior performance in terms of the accuracy, while having high running speed.
科研通智能强力驱动
Strongly Powered by AbleSci AI