Papers
arxiv:2312.00824

Variational Self-Supervised Contrastive Learning Using Beta Divergence

Published on May 8, 2024
Authors:
,

Abstract

A contrastive self-supervised method using variational contrastive learning with beta-divergence learns robustly from unlabeled noisy multi-label data and outperforms existing self-supervised methods on face understanding tasks.

Learning a discriminative semantic space using unlabelled and noisy data remains unaddressed in a multi-label setting. We present a contrastive self-supervised learning method which is robust to data noise, grounded in the domain of variational methods. The method (VCL) utilizes variational contrastive learning with beta-divergence to learn robustly from unlabelled datasets, including uncurated and noisy datasets. We demonstrate the effectiveness of the proposed method through rigorous experiments including linear evaluation and fine-tuning scenarios with multi-label datasets in the face understanding domain. In almost all tested scenarios, VCL surpasses the performance of state-of-the-art self-supervised methods, achieving a noteworthy increase in accuracy.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2312.00824
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2312.00824 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2312.00824 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.