English

Deep Metric Learning for Computer Vision: A Brief Overview

Computer Vision and Pattern Recognition 2023-12-19 v1 Artificial Intelligence Information Retrieval Machine Learning

Abstract

Objective functions that optimize deep neural networks play a vital role in creating an enhanced feature representation of the input data. Although cross-entropy-based loss formulations have been extensively used in a variety of supervised deep-learning applications, these methods tend to be less adequate when there is large intra-class variance and low inter-class variance in input data distribution. Deep Metric Learning seeks to develop methods that aim to measure the similarity between data samples by learning a representation function that maps these data samples into a representative embedding space. It leverages carefully designed sampling strategies and loss functions that aid in optimizing the generation of a discriminative embedding space even for distributions having low inter-class and high intra-class variances. In this chapter, we will provide an overview of recent progress in this area and discuss state-of-the-art Deep Metric Learning approaches.

Keywords

Cite

@article{arxiv.2312.10046,
  title  = {Deep Metric Learning for Computer Vision: A Brief Overview},
  author = {Deen Dayal Mohan and Bhavin Jawade and Srirangaraj Setlur and Venu Govindaraj},
  journal= {arXiv preprint arXiv:2312.10046},
  year   = {2023}
}

Comments

Book Chapter Published In Handbook of Statistics, Special Issue - Deep Learning 48, 59

R2 v1 2026-06-28T13:52:48.572Z