Feature Distilled Tracking | |
Zhu Guibo1; Jinqiao Wang1,2; Peisong Wang1,2; Yi Wu3,4; Hanqing Lu1,2 | |
刊名 | IEEE Transaction on Cybernetics |
2017-12 | |
期号 | 0页码:0 |
关键词 | Correlation Filter Model Compression Visual Tracking |
DOI | 10.1109/TCYB.2017.2776977 |
英文摘要 |
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.
|
学科主题 | Computer Science, Artificial Intelligence, Cybernetics |
语种 | 英语 |
WOS记录号 | WOS:3 |
资助机构 | National Natural Science Foundation of China under Grant 61702510, Grant 61773375, Grant 61370036, Grant 61772277, and Grant 61772527. |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/22062] |
专题 | 自动化研究所_模式识别国家重点实验室_图像与视频分析团队 |
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. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论