中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Unstructured Feature Decoupling for Vehicle Re-identification

文献类型:会议论文

作者Wen Qian1,3; Hao Luo2; Silong Peng1,3; Fan Wang2; Chen Chen1
出版日期2022-10
会议日期October 23–27, 2022
会议地点Tel Aviv, Israel
英文摘要

   The misalignment of features caused by pose and viewpoint variances is a crucial problem in Vehicle Re-Identification (ReID).
   Previous methods align the features by structuring the vehicles from pre-defined vehicle parts (such as logos, windows, etc.) or attributes, which are inefficient because of additional manual annotation.
   To align the features without requirements of additional annotation, this paper proposes a \textbf{Unstructured Feature Decoupling Network} (UFDN), which consists of a transformer-based feature decomposing head (TDH) and a novel cluster-based decoupling constraint (CDC).
   Different from the structured knowledge used in previous decoupling methods, we aim to achieve more flexible unstructured decoupled features with diverse discriminative information as shown in Fig. \ref{fig:intro}.
   The self-attention mechanism in the decomposing head helps the model preliminarily learn the discriminative decomposed features in a global scope. 
   To further learn diverse but aligned decoupled features, we introduce a cluster-based decoupling constraint consisting of a diversity constraint and an alignment constraint.
  Furthermore, we improve the alignment constraint into a modulated one to eliminate the negative impact of the outlier features that cannot align the clusters in semantics.
   Extensive experiments show the proposed UFDN achieves state-of-the-art performance on three popular Vehicle ReID benchmarks with both CNN and Transformer backbones. 

源URL[http://ir.ia.ac.cn/handle/173211/51915]  
专题自动化研究所_智能制造技术与系统研究中心_多维数据分析团队
通讯作者Chen Chen
作者单位1.自动化所
2.阿里巴巴
3.中国科学院大学
推荐引用方式
GB/T 7714
Wen Qian,Hao Luo,Silong Peng,et al. Unstructured Feature Decoupling for Vehicle Re-identification[C]. 见:. Tel Aviv, Israel. October 23–27, 2022.

入库方式: OAI收割

来源:自动化研究所

浏览0
下载0
收藏0
其他版本

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。