A Metric Learning Reality Check

03/18/2020
by   Kevin Musgrave, et al.
85

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/05/2012

Robustness and Generalization for Metric Learning

Metric learning has attracted a lot of interest over the last decade, bu...
research
02/26/2020

Supervised Categorical Metric Learning with Schatten p-Norms

Metric learning has been successful in learning new metrics adapted to n...
research
10/03/2022

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

Version identification (VI) has seen substantial progress over the past ...
research
01/06/2023

Triple-stream Deep Metric Learning of Great Ape Behavioural Actions

We propose the first metric learning system for the recognition of great...
research
08/20/2020

PyTorch Metric Learning

Deep metric learning algorithms have a wide variety of applications, but...
research
12/17/2021

Visual Microfossil Identificationvia Deep Metric Learning

We apply deep metric learning for the first time to the prob-lem of clas...
research
12/29/2022

HIER: Metric Learning Beyond Class Labels via Hierarchical Regularization

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

Please sign up or login with your details

Forgot password? Click here to reset