Salience-guided cascaded suppression network for person re-identification

Chen，Xuesong1,2,8; Fu，Canmiao3; Zhao，Yong1; Zheng，Feng2; Song，Jingkuan6; Ji，Rongrong4,7; Yang，Yi5

10.1109/CVPR42600.2020.00336

2020

1063-6919

978-1-7281-7169-2

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

3297-3307

13-19 June 2020

Seattle, WA, USA

Employing attention mechanisms to model both global and local features as a final pedestrian representation has become a trend for person re-identification (Re-ID) algorithms. A potential limitation of these methods is that they focus on the most salient features, but the re-identification of a person may rely on diverse clues masked by the most salient features in different situations, e.g., body, clothes or even shoes. To handle this limitation, we propose a novel Salience-guided Cascaded Suppression Network (SCSN) which enables the model to mine diverse salient features and integrate these features into the final representation by a cascaded manner. Our work makes the following contributions: (i) We observe that the previously learned salient features may hinder the network from learning other important information. To tackle this limitation, we introduce a cascaded suppression strategy, which enables the network to mine diverse potential useful features that be masked by the other salient features stage-by-stage and each stage integrates different feature embedding for the last discriminative pedestrian representation. (ii) We propose a Salient Feature Extraction (SFE) unit, which can suppress the salient features learned in the previous cascaded stage and then adaptively extracts other potential salient feature to obtain different clues of pedestrians. (iii) We develop an efficient feature aggregation strategy that fully increases the network's capacity for all potential salience features. Finally, experimental results demonstrate that our proposed method outperforms the state-of-the-art methods on four large-scale datasets. Especially, our approach exceeds the current best method by over 7% on the CUHK03 dataset.

Feature extraction Semantics Aggregates Training Testing Task analysis Biological system modeling

通讯

英语

EI

20204409424826

Computer vision

Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Vision:741.2

2-s2.0-85094173901

Scopus

1.School of Electronic and Computer Engineering,Peking University,China
2.Southern University of Science and Technology,China
3.Tencent,China
4.Xiamen University,China
5.ReLER Lab,Centre for AI,University of Technology,Sydney,Australia
6.University of Electronic Science and Technology of China,China
7.Peng Cheng Laboratory,China
8.Feng Zheng Lab,SUSTech,China

Chen，Xuesong,Fu，Canmiao,Zhao，Yong,et al. Salience-guided cascaded suppression network for person re-identification[C],2020:3297-3307.