DeepAI AI Chat
Log In Sign Up

A Metric Learning Reality Check

by   Kevin Musgrave, et al.

Deep metric learning papers from the past four years have consistently claimed great advances in accuracy, often more than doubling the performance of decade-old methods. In this paper, we take a closer look at the field to see if this is actually true. We find flaws in the experimental setup of these papers, and propose a new way to evaluate metric learning algorithms. Finally, we present experimental results that show that the improvements over time have been marginal at best.


page 1

page 2

page 3

page 4


Robustness and Generalization for Metric Learning

Metric learning has attracted a lot of interest over the last decade, bu...

Supervised Categorical Metric Learning with Schatten p-Norms

Metric learning has been successful in learning new metrics adapted to n...

And what if two musical versions don't share melody, harmony, rhythm, or lyrics ?

Version identification (VI) has seen substantial progress over the past ...

Triple-stream Deep Metric Learning of Great Ape Behavioural Actions

We propose the first metric learning system for the recognition of great...

PyTorch Metric Learning

Deep metric learning algorithms have a wide variety of applications, but...

Visual Microfossil Identificationvia Deep Metric Learning

We apply deep metric learning for the first time to the prob-lem of clas...

HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization

Supervision for metric learning has long been given in the form of equiv...

Code Repositories


A PyTorch library for benchmarking deep metric learning. It's powerful.

view repo