Saved in:
Bibliographic Details
Main Authors: Bhatnagar, Shubhang, Ahuja, Narendra
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.14977
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911809099792384
author Bhatnagar, Shubhang
Ahuja, Narendra
author_facet Bhatnagar, Shubhang
Ahuja, Narendra
contents Unsupervised deep metric learning (UDML) focuses on learning a semantic representation space using only unlabeled data. This challenging problem requires accurately estimating the similarity between data points, which is used to supervise a deep network. For this purpose, we propose to model the high-dimensional data manifold using a piecewise-linear approximation, with each low-dimensional linear piece approximating the data manifold in a small neighborhood of a point. These neighborhoods are used to estimate similarity between data points. We empirically show that this similarity estimate correlates better with the ground truth than the similarity estimates of current state-of-the-art techniques. We also show that proxies, commonly used in supervised metric learning, can be used to model the piecewise-linear manifold in an unsupervised setting, helping improve performance. Our method outperforms existing unsupervised metric learning approaches on standard zero-shot image retrieval benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2403_14977
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Piecewise-Linear Manifolds for Deep Metric Learning
Bhatnagar, Shubhang
Ahuja, Narendra
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Image and Video Processing
Unsupervised deep metric learning (UDML) focuses on learning a semantic representation space using only unlabeled data. This challenging problem requires accurately estimating the similarity between data points, which is used to supervise a deep network. For this purpose, we propose to model the high-dimensional data manifold using a piecewise-linear approximation, with each low-dimensional linear piece approximating the data manifold in a small neighborhood of a point. These neighborhoods are used to estimate similarity between data points. We empirically show that this similarity estimate correlates better with the ground truth than the similarity estimates of current state-of-the-art techniques. We also show that proxies, commonly used in supervised metric learning, can be used to model the piecewise-linear manifold in an unsupervised setting, helping improve performance. Our method outperforms existing unsupervised metric learning approaches on standard zero-shot image retrieval benchmarks.
title Piecewise-Linear Manifolds for Deep Metric Learning
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Image and Video Processing
url https://arxiv.org/abs/2403.14977