LM-Metric: Learned pair weighting and contextual memory for deep metric learning

Shiyang Yan, Lin Xu, Xinyao Shu, Zhenyu Lu, Jialie Shen

Abstract: Highlights•We propose a policy gradient-based meta-learned parametric metric learning scheme (LM-Metric).•We consider the inter-sample relationship during training to solve the non-decomposability problem of AP optimization.•We validate the effectiveness of our method, by applying it to variouis (DML) loss, e.g., Triplet, Margin, and Proxy-anchor losses.