A Deep and Structured Metric Learning Method for Robust Person Re-Identification
作者：
Highlights：
• We propose a new method for deep metric learning and discriminant feature extraction. In formulating the loss function, the positive pairs of small distances and negative pairs of large distances are simultaneously removed to improve learning efficiency and prediction accuracy.
• To address the class-imbalance problem, a penalty factor is assigned to the negative pair distance. By using a linear function with the margin-based objectives, the weights update process is robust to large iterative loss values.
• The loss function is compatible with many network backbones. It thus can be used to induce new deep methods for metric learning. The method with the ResNet-50 backbone is used for person re-ID, and extensive experiments on benchmark datasets validate the effectiveness.
摘要
•We propose a new method for deep metric learning and discriminant feature extraction. In formulating the loss function, the positive pairs of small distances and negative pairs of large distances are simultaneously removed to improve learning efficiency and prediction accuracy.•To address the class-imbalance problem, a penalty factor is assigned to the negative pair distance. By using a linear function with the margin-based objectives, the weights update process is robust to large iterative loss values.•The loss function is compatible with many network backbones. It thus can be used to induce new deep methods for metric learning. The method with the ResNet-50 backbone is used for person re-ID, and extensive experiments on benchmark datasets validate the effectiveness.
论文关键词：Metric learning,Feature extraction,Deep neural networks,Imbalance regularization,Person re-identification
论文评审过程：Received 3 February 2019, Revised 18 July 2019, Accepted 31 July 2019, Available online 1 August 2019, Version of Record 9 August 2019.
论文官网地址：https://doi.org/10.1016/j.patcog.2019.106995
