Deep View-Aware Metric Learning for Person Re-Identification

Deep View-Aware Metric Learning for Person Re-Identification

Pu Chen, Xinyi Xu, Cheng Deng

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 620-626. https://doi.org/10.24963/ijcai.2018/86

Person re-identification remains a challenging issue due to the dramatic changes in visual appearance caused by the variations in camera views, human pose, and background clutter. In this paper, we propose a deep view-aware metric learning (DVAML) model, where image pairs with similar and dissimilar views are projected into different feature subspaces, which can discover the intrinsic relevance between image pairs from different aspects. Additionally, we employ multiple metrics to jointly learn feature subspaces on which the relevance between image pairs are explicitly captured and thus greatly promoting the retrieval accuracy. Extensive experiment results on datasets CUHK01, CUHK03, and PRID2011 demonstrate the superiority of our method compared with state-of-the-art approaches.
Keywords:
Machine Learning: Deep Learning
Computer Vision: Recognition: Detection, Categorization, Indexing, Matching, Retrieval, Semantic Interpretation