Transductive semi-supervised metric learning for person re-identification

作者：

Highlights：

• We propose the Transductive Semi-Supervised Metric Learning (TSSML) framework to solve the open-set semi-supervised ReID problem.

• We propose a graph-based transductive hard mining method for deeply mining hard pairwise relationships and a degree-based relationship confidence scoring method for reducing the negative effect of incorrect pairwise relationships.

• We investigate the feature consistency loss to improve the robustness of the model and adopt the curriculum learning strategy to have a better optimization process.

摘要

•We propose the Transductive Semi-Supervised Metric Learning (TSSML) framework to solve the open-set semi-supervised ReID problem.•We propose a graph-based transductive hard mining method for deeply mining hard pairwise relationships and a degree-based relationship confidence scoring method for reducing the negative effect of incorrect pairwise relationships.•We investigate the feature consistency loss to improve the robustness of the model and adopt the curriculum learning strategy to have a better optimization process.

论文关键词：Person re-identification,Transductive learning,Semi-supervised learning,Graph,Confidence score

论文评审过程：Received 2 December 2019, Revised 10 July 2020, Accepted 28 July 2020, Available online 4 August 2020, Version of Record 10 August 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2020.107569