|
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.
|