Probabilistic Contrastive Learning with Explicit Concentration on the Hypersphere

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Hongwei Bran, Ouyang, Cheng, Amiranashvili, Tamaz, Rosen, Matthew S., Menze, Bjoern, Iglesias, Juan Eugenio
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916261131190272
author Li, Hongwei Bran
Ouyang, Cheng
Amiranashvili, Tamaz
Rosen, Matthew S.
Menze, Bjoern
Iglesias, Juan Eugenio
author_facet Li, Hongwei Bran
Ouyang, Cheng
Amiranashvili, Tamaz
Rosen, Matthew S.
Menze, Bjoern
Iglesias, Juan Eugenio
contents Self-supervised contrastive learning has predominantly adopted deterministic methods, which are not suited for environments characterized by uncertainty and noise. This paper introduces a new perspective on incorporating uncertainty into contrastive learning by embedding representations within a spherical space, inspired by the von Mises-Fisher distribution (vMF). We introduce an unnormalized form of vMF and leverage the concentration parameter, kappa, as a direct, interpretable measure to quantify uncertainty explicitly. This approach not only provides a probabilistic interpretation of the embedding space but also offers a method to calibrate model confidence against varying levels of data corruption and characteristics. Our empirical results demonstrate that the estimated concentration parameter correlates strongly with the degree of unforeseen data corruption encountered at test time, enables failure analysis, and enhances existing out-of-distribution detection methods.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16460
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Probabilistic Contrastive Learning with Explicit Concentration on the Hypersphere
Li, Hongwei Bran
Ouyang, Cheng
Amiranashvili, Tamaz
Rosen, Matthew S.
Menze, Bjoern
Iglesias, Juan Eugenio
Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
Self-supervised contrastive learning has predominantly adopted deterministic methods, which are not suited for environments characterized by uncertainty and noise. This paper introduces a new perspective on incorporating uncertainty into contrastive learning by embedding representations within a spherical space, inspired by the von Mises-Fisher distribution (vMF). We introduce an unnormalized form of vMF and leverage the concentration parameter, kappa, as a direct, interpretable measure to quantify uncertainty explicitly. This approach not only provides a probabilistic interpretation of the embedding space but also offers a method to calibrate model confidence against varying levels of data corruption and characteristics. Our empirical results demonstrate that the estimated concentration parameter correlates strongly with the degree of unforeseen data corruption encountered at test time, enables failure analysis, and enhances existing out-of-distribution detection methods.
title Probabilistic Contrastive Learning with Explicit Concentration on the Hypersphere
topic Machine Learning
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.16460