Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval

Frederik Warburg, Marco Miani, Silas Brack, Søren Hauberg

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

32 Downloads (Pure)

Abstract

We propose the first Bayesian encoder for metric learning. Rather than relying on neural amortization as done in prior works, we learn a distribution over the network weights with the Laplace Approximation. We actualize this by first proving that the contrastive loss is a valid log-posterior. We then propose three methods that ensure a positive definite Hessian. Lastly, we present a novel decomposition of the Generalized Gauss-Newton approximation. Empirically, we show that our Laplacian Metric Learner (LAM) estimates wellcalibrated uncertainties, reliably detects out-ofdistribution examples, and yields state-of-the-art
predictive performance.
Original languageEnglish
Title of host publicationProceedings of the 37th Conference on Neural Information Processing Systems
Number of pages26
Volume36
PublisherNeural Information Processing Systems Foundation
Publication statusAccepted/In press - 2024
Event37th Conference on Neural Information Processing Systems - New Orleans Ernest N. Morial Convention Center, New Orleans, United States
Duration: 10 Dec 202316 Dec 2023

Conference

Conference37th Conference on Neural Information Processing Systems
LocationNew Orleans Ernest N. Morial Convention Center
Country/TerritoryUnited States
CityNew Orleans
Period10/12/202316/12/2023

Fingerprint

Dive into the research topics of 'Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval'. Together they form a unique fingerprint.

Cite this