.png){kind=icon}
返回
Deep Decoupling Classification and Regression for Visual Tracking
.png){kind=icon}
PRE
AI
DOI：10.1109/TCDS.2022.3202802.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Classification and regression are two tasks that most Siamese-based trackers need to handle. However, most of the existing trackers only learn one feature embedding to handle these two types of task, making it difficult to optimize both simultaneously. To solve this problem, this article tries to deeply decouple classification and regression in the model structure. Specifically, two feature extraction backbone networks are used to divide the model into two branches to extract the heterogeneous features suitable for the two tasks, respectively. Inspired by the core idea of transformer, information interaction and fusion between multiple branches are achieved by the cross-attention mechanism, which can fully exploit the deep information dependence between multiple branches. In addition, the concept of channel-level information interaction is proposed by innovatively changing the generation mode of vector groups in the attention module. The experiments show that double Siamese tracker (DST) designed in this article greatly improves the accuracy of classification and regression. DST runs at 60 frames per second (FPS) on GPU, far above the real-time requirement.
Keyword:
Attention mechanism
Siamese network
transformer
visual tracking
期刊
IF:
4.9
论文数:
1.0K
被引数:
3.5K
机构
引用论文
A novel flake-ball-like magnetic Fe3O4/γ-MnO2 meso-porous nano-composite: Adsorption of fluorinion and effect of water chemistry.png)
Chemosphere
ChemosphereIF0
PREAI
分享收藏An efficient self-attention network for skeleton-based action recognitionSCIENTIFIC REPORTS
OAAI
SCIENTIFIC REPORTSIF3.9
OAAI分享收藏Role of Urban Landscapes in Changing the Irrigation Water Requirements in Arid ClimateGeosciences
OAAI
GeosciencesIF0
OAAI分享收藏Geriatric Assessments and Medication Therapy Management Approaches in Elderly Oncology Patients
PREAI
分享收藏
查看更多内容