DSIC: DYNAMIC SAMPLE-INDIVIDUALIZED CONNECTOR FOR MULTI-SCALE OBJECT DETECTION | |
Li Zekun4,5; Liu Yufan4,5; Li Bing3,4,5; Hu Weiming1,4,5; Miao Yanan2; Zhang Hong2 | |
2021 | |
会议日期 | 2021.07 |
会议地点 | 线上 |
英文摘要 | 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 S election 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 infor mative data flow paths based on the extracted multi-level fea tures. 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. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48856] |
专题 | 自动化研究所_模式识别国家重点实验室_视频内容安全团队 |
通讯作者 | Li Bing |
作者单位 | 1.CAS Center for Excellence in Brain Science and Intelligence Technology 2.National Computer Network Emergency Response Technical Team/Coordination Center of China 3.PeopleAI Inc 4.School of Artificial Intelligence, University of Chinese Academy of Sciences 5.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Li Zekun,Liu Yufan,Li Bing,et al. DSIC: DYNAMIC SAMPLE-INDIVIDUALIZED CONNECTOR FOR MULTI-SCALE OBJECT DETECTION[C]. 见:. 线上. 2021.07. |
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