Feature Distilled Tracking
Zhu Guibo1; Jinqiao Wang1,2; Peisong Wang1,2; Yi Wu3,4; Hanqing Lu1,2
2017-12
发表期刊IEEE Transaction on Cybernetics
期号0页码:0
摘要
Feature extraction and representation is one of the most important components for fast, accurate, and robust visual tracking. Very deep convolutional neural networks (CNNs) provide effective tools for feature extraction with good generalization ability. However, extracting features using very deep CNN models needs high performance hardware due to its large computation complexity, which prohibits its extensions in real-time applications. To alleviate this problem, we aim at obtaining small and fast-to-execute shallow models based on model compression for visual tracking. Specifically, we propose a small feature distilled network (FDN) for tracking by imitating the intermediate representations of a much deeper network. The FDN extracts rich visual features with higher speed than the original deeper network. To further speed-up, we introduce a shift-and-stitch method to reduce the arithmetic operations, while preserving the spatial resolution of the distilled feature maps unchanged. Finally, a scale adaptive discriminative correlation filter is learned on the distilled feature for visual tracking to handle scale variation of the target. Comprehensive experimental results on object tracking benchmark datasets show that the proposed approach achieves 5x speed-up with competitive performance to the state-of-the-art deep trackers.
 
关键词Correlation Filter Model Compression Visual Tracking
学科领域Computer Science, Artificial Intelligence, Cybernetics
DOI10.1109/TCYB.2017.2776977
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China under Grant 61702510, Grant 61773375, Grant 61370036, Grant 61772277, and Grant 61772527.
WOS记录号WOS:3
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/22062
专题模式识别国家重点实验室_图像与视频分析
通讯作者Jinqiao Wang
作者单位1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.Nanjing Audit University
4.Indiana University School of Medicine
推荐引用方式
GB/T 7714
Zhu Guibo,Jinqiao Wang,Peisong Wang,et al. Feature Distilled Tracking[J]. IEEE Transaction on Cybernetics,2017(0):0.
APA Zhu Guibo,Jinqiao Wang,Peisong Wang,Yi Wu,&Hanqing Lu.(2017).Feature Distilled Tracking.IEEE Transaction on Cybernetics(0),0.
MLA Zhu Guibo,et al."Feature Distilled Tracking".IEEE Transaction on Cybernetics .0(2017):0.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
feature distilled tr(2450KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhu Guibo]的文章
[Jinqiao Wang]的文章
[Peisong Wang]的文章
百度学术
百度学术中相似的文章
[Zhu Guibo]的文章
[Jinqiao Wang]的文章
[Peisong Wang]的文章
必应学术
必应学术中相似的文章
[Zhu Guibo]的文章
[Jinqiao Wang]的文章
[Peisong Wang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: feature distilled tracking.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。