Online learning discriminative sparse convolution networks for robust UAV object tracking

IF 7.2 1区 计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE
Qi Xu , Zhuoming Xu , Huabin Wang , Yun Chen , Liang Tao
{"title":"Online learning discriminative sparse convolution networks for robust UAV object tracking","authors":"Qi Xu ,&nbsp;Zhuoming Xu ,&nbsp;Huabin Wang ,&nbsp;Yun Chen ,&nbsp;Liang Tao","doi":"10.1016/j.knosys.2024.112742","DOIUrl":null,"url":null,"abstract":"<div><div>Despite the remarkable empirical success for UAV object tracking, current convolutional networks usually have three unavoidable limitations: (1) The feature maps produced by convolutional layers are difficult to interpret. (2) The network needs to be trained offline on a large-scale auxiliary training set, resulting in the feature extraction ability of the trained network depending on the categories of the training set. (3) The performance of networks suffers from sensitivity to hyper-parameters (such as learning rate and weight decay) when the network needs online fine-tuning. To overcome the three limitations, this paper proposes a Discriminative Sparse Convolutional Network (DSCN) that exhibits good layer-wise interpretability and can be trained online without requiring any auxiliary training data. By imposing sparsity constraints on the convolutional kernels, DSCN furnishes the convolution layer with an explicit data meaning, thus enhancing the interpretability of the feature maps. These convolutional kernels are directly learned online from image blocks, which eliminates the offline training process on auxiliary data sets. Moreover, a simple yet effective online tuning method with few hyper-parameters is proposed to fine-tune fully connected layers online. We have successfully applied DSCN to UAV object tracking and conducted extensive experiments on six mainstream UAV datasets. The experimental results demonstrate that our method performs favorably against several state-of-the-art tracking algorithms in terms of tracking accuracy and robustness.</div></div>","PeriodicalId":49939,"journal":{"name":"Knowledge-Based Systems","volume":"308 ","pages":"Article 112742"},"PeriodicalIF":7.2000,"publicationDate":"2024-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Knowledge-Based Systems","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0950705124013765","RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0

Abstract

Despite the remarkable empirical success for UAV object tracking, current convolutional networks usually have three unavoidable limitations: (1) The feature maps produced by convolutional layers are difficult to interpret. (2) The network needs to be trained offline on a large-scale auxiliary training set, resulting in the feature extraction ability of the trained network depending on the categories of the training set. (3) The performance of networks suffers from sensitivity to hyper-parameters (such as learning rate and weight decay) when the network needs online fine-tuning. To overcome the three limitations, this paper proposes a Discriminative Sparse Convolutional Network (DSCN) that exhibits good layer-wise interpretability and can be trained online without requiring any auxiliary training data. By imposing sparsity constraints on the convolutional kernels, DSCN furnishes the convolution layer with an explicit data meaning, thus enhancing the interpretability of the feature maps. These convolutional kernels are directly learned online from image blocks, which eliminates the offline training process on auxiliary data sets. Moreover, a simple yet effective online tuning method with few hyper-parameters is proposed to fine-tune fully connected layers online. We have successfully applied DSCN to UAV object tracking and conducted extensive experiments on six mainstream UAV datasets. The experimental results demonstrate that our method performs favorably against several state-of-the-art tracking algorithms in terms of tracking accuracy and robustness.
在线学习判别稀疏卷积网络,实现稳健的无人飞行器目标跟踪
尽管卷积网络在无人机物体跟踪方面取得了显著的经验成功,但目前的卷积网络通常存在三个不可避免的局限性:(1)卷积层产生的特征图难以解释。(2)网络需要在大规模辅助训练集上进行离线训练,导致训练网络的特征提取能力取决于训练集的类别。(3) 当网络需要在线微调时,网络性能会受到超参数(如学习率和权重衰减)的影响。为了克服上述三个局限性,本文提出了一种判别稀疏卷积网络(DSCN),它具有良好的层向可解释性,并且无需任何辅助训练数据即可进行在线训练。通过对卷积核施加稀疏性约束,DSCN 为卷积层提供了明确的数据含义,从而提高了特征图的可解释性。这些卷积核直接从图像块中在线学习,从而省去了在辅助数据集上的离线训练过程。此外,我们还提出了一种简单而有效的在线调整方法,只需几个超参数就能在线微调全连接层。我们成功地将 DSCN 应用于无人机物体跟踪,并在六个主流无人机数据集上进行了广泛的实验。实验结果表明,我们的方法在跟踪精度和鲁棒性方面优于几种最先进的跟踪算法。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Knowledge-Based Systems
Knowledge-Based Systems 工程技术-计算机:人工智能
CiteScore
14.80
自引率
12.50%
发文量
1245
审稿时长
7.8 months
期刊介绍: Knowledge-Based Systems, an international and interdisciplinary journal in artificial intelligence, publishes original, innovative, and creative research results in the field. It focuses on knowledge-based and other artificial intelligence techniques-based systems. The journal aims to support human prediction and decision-making through data science and computation techniques, provide a balanced coverage of theory and practical study, and encourage the development and implementation of knowledge-based intelligence models, methods, systems, and software tools. Applications in business, government, education, engineering, and healthcare are emphasized.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信