No Fuss Distance Metric Learning Using Proxies

Abstract

We address the problem of distance metric learning (DML), defined as learning a distance consistent with a notion of semantic similarity. Traditionally, for this problem supervision is expressed in the form of sets of points that follow an ordinal relationship -- an anchor point \(x\) is similar to a set of positive points \(Y\), and dissimilar to a set of negative points \(Z\), and a loss defined over these distances is minimized. While the specifics of the optimization differ, in this work we collectively call this type of supervision Triplets and all methods that follow this pattern Triplet-Based methods. These methods are challenging to optimize. A main issue is the need for finding informative triplets, which is usually achieved by a variety of tricks such as increasing the batch size, hard or semi-hard triplet mining, etc. Even with these tricks, the convergence rate of such methods is slow. In this paper we propose to optimize the triplet loss on a different space of triplets, c

Stats

• citations468
• S2 citations—
• github stars0
• HF likes0
• heat score20.03
• arxiv keymovshovitzattias2017no

Related papers

• Deep Metric Learning With Soft Orthogonal Proxies (2023)0.00
• Towards Improved Proxy-based Deep Metric Learning Via Data-augmented Domain Adaptation (2024)6.34
• Procsim: Proxy-based Confidence For Robust Similarity Learning (2023)0.00
• Large-scale Distance Metric Learning With Uncertainty (2018)9.03
• Hierarchical Proxy-based Loss For Deep Metric Learning (2021)10.85
• Piecewise-linear Manifolds For Deep Metric Learning (2024)0.00
• Guided Deep Metric Learning (2022)6.77
• Multi-head Deep Metric Learning Using Global And Local Representations (2021)6.77