English

Affinity guided Geometric Semi-Supervised Metric Learning

Computer Vision and Pattern Recognition 2020-11-09 v2 Machine Learning

Abstract

In this paper, we revamp the forgotten classical Semi-Supervised Distance Metric Learning (SSDML) problem from a Riemannian geometric lens, to leverage stochastic optimization within a end-to-end deep framework. The motivation comes from the fact that apart from a few classical SSDML approaches learning a linear Mahalanobis metric, deep SSDML has not been studied. We first extend existing SSDML methods to their deep counterparts and then propose a new method to overcome their limitations. Due to the nature of constraints on our metric parameters, we leverage Riemannian optimization. Our deep SSDML method with a novel affinity propagation based triplet mining strategy outperforms its competitors.

Keywords

Cite

@article{arxiv.2002.12394,
  title  = {Affinity guided Geometric Semi-Supervised Metric Learning},
  author = {Ujjal Kr Dutta and Mehrtash Harandi and Chellu Chandra Sekhar},
  journal= {arXiv preprint arXiv:2002.12394},
  year   = {2020}
}

Comments

Paper accepted in NeurIPS 2020 workshop on Differential Geometry meets Deep Learning

R2 v1 2026-06-23T13:56:49.085Z