Piecewise-linear Manifolds For Deep Metric Learning

Abstract

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 be

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybhatnagar2024piecewise

Related papers

• Deep Metric Learning Meets Deep Clustering: An Novel Unsupervised Approach For Feature Embedding (2020)2.26
• Metric Learning On Manifolds (2019)0.00
• Guided Deep Metric Learning (2022)6.77
• Mining On Manifolds: Metric Learning Without Labels (2018)14.31
• No Fuss Distance Metric Learning Using Proxies (2017)20.03
• Large-scale Distance Metric Learning With Uncertainty (2018)9.03
• Deep Metric Learning Using Similarities From Nonlinear Rank Approximations (2019)2.26
• Improving Deep Metric Learning By Divide And Conquer (2021)8.09