Online Feature Classification and Clustering for Transformer-based Visual Tracker | |
Zhuojun Zou2,3; Jie Hao1,3; Lin Shu1,3 | |
2022-08 | |
会议日期 | 21-25 August 2022 |
会议地点 | Montreal, QC, Canada |
英文摘要 | Compared with the current booming development of siamese tracking network, online optimization methods for tracking models still update parameters or features in pulses, which is non-real-time and on whole image level. In the past year, similarity measurement components derived from Transformer equiped on Siamese networks have obtained excellent performance in visual tracking task. Leveraging its element-wise attention mechanism, we implement a real-time feature update approach on coarse pixel level. We first construct a classification branch for quality control; and to further reduce the feature amount in online update process, we apply an incremental clustering method to minimize the repetitive contribution of similar features. The proposed method is evaluated on multiple datasets including OTB2015, NfS and GOT-10k. It exceeds the baseline methods on all 3 datasets and achieves competitive performance against the state-of-the-art networks. |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/52270] |
专题 | 国家专用集成电路设计工程技术研究中心_实感计算 |
通讯作者 | Jie Hao |
作者单位 | 1.Guangdong Institute of Artificial Intelligence and Advanced Computing 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.Institute of Automation, Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Zhuojun Zou,Jie Hao,Lin Shu. Online Feature Classification and Clustering for Transformer-based Visual Tracker[C]. 见:. Montreal, QC, Canada. 21-25 August 2022. |
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