English

Learning Empirical Bregman Divergence for Uncertain Distance Representation

Computer Vision and Pattern Recognition 2023-08-30 v3 Artificial Intelligence Information Theory Machine Learning math.IT Machine Learning

Abstract

Deep metric learning techniques have been used for visual representation in various supervised and unsupervised learning tasks through learning embeddings of samples with deep networks. However, classic approaches, which employ a fixed distance metric as a similarity function between two embeddings, may lead to suboptimal performance for capturing the complex data distribution. The Bregman divergence generalizes measures of various distance metrics and arises throughout many fields of deep metric learning. In this paper, we first show how deep metric learning loss can arise from the Bregman divergence. We then introduce a novel method for learning empirical Bregman divergence directly from data based on parameterizing the convex function underlying the Bregman divergence with a deep learning setting. We further experimentally show that our approach performs effectively on five popular public datasets compared to other SOTA deep metric learning methods, particularly for pattern recognition problems.

Keywords

Cite

@article{arxiv.2304.07689,
  title  = {Learning Empirical Bregman Divergence for Uncertain Distance Representation},
  author = {Zhiyuan Li and Ziru Liu and Anna Zou and Anca L. Ralescu},
  journal= {arXiv preprint arXiv:2304.07689},
  year   = {2023}
}

Comments

Accepted by IEEE FUSION 2023

R2 v1 2026-06-28T10:07:16.792Z