CASIA OpenIR  > 模式识别国家重点实验室  > 视频内容安全
DSIC: DYNAMIC SAMPLE-INDIVIDUALIZED CONNECTOR FOR MULTI-SCALE OBJECT DETECTION
Li Zekun1,2; Liu Yufan1,2; Li Bing1,2,3; Hu Weiming1,2,5; Miao Yanan4; Zhang Hong4
2021
Conference NameInternational Conference on Multimedia & Expo
Conference Date2021.07
Conference Place线上
Abstract

Although object detection has reached a milestone recently, the scale variation is still the key challenge. Integrating multi-level features is presented to alleviate the problems, like Feature Pyramid Network (FPN) and its improvements. However, the specifically designed architectures and fixed data flow paths of these methods are not flexible for feature fusion, especially when fed with various samples. To overcome the limitations, we propose a Dynamic Sample-Individualized Connector (DSIC) for multi-scale object detection, which dynamically adjusts network connections to fit different samples. In particular, DSIC consists of two components: Intra-scale Selection Gate (ISG) and Cross-scale Selection Gate (CSG). With the help of the presented gate operator, ISG adaptively extracts proper multi-level features from backbone as the inputs of feature integration. CSG automatically activates informative data flow paths based on the extracted multi-level features. These two components are both plug-and-play and can be embedded in any backbone. Experimental results demonstrate that the proposed method outperforms the state-of-the-arts.

Document Type会议论文
Identifierhttp://ir.ia.ac.cn/handle/173211/48856
Collection模式识别国家重点实验室_视频内容安全
Corresponding AuthorLi Bing
Affiliation1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences
2.School of Artificial Intelligence, University of Chinese Academy of Sciences
3.PeopleAI Inc
4.National Computer Network Emergency Response Technical Team/Coordination Center of China
5.CAS Center for Excellence in Brain Science and Intelligence Technology
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Corresponding Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Li Zekun,Liu Yufan,Li Bing,et al. DSIC: DYNAMIC SAMPLE-INDIVIDUALIZED CONNECTOR FOR MULTI-SCALE OBJECT DETECTION[C],2021.
Files in This Item: Download All
File Name/Size DocType Version Access License
dsic.pdf(1487KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Li Zekun]'s Articles
[Liu Yufan]'s Articles
[Li Bing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Li Zekun]'s Articles
[Liu Yufan]'s Articles
[Li Bing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Li Zekun]'s Articles
[Liu Yufan]'s Articles
[Li Bing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: dsic.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.