Conditional Alignment and Uniformity for Contrastive Learning with Continuous Proxy Labels

11/10/2021
by   Benoit Dufumier, et al.
0

Contrastive Learning has shown impressive results on natural and medical images, without requiring annotated data. However, a particularity of medical images is the availability of meta-data (such as age or sex) that can be exploited for learning representations. Here, we show that the recently proposed contrastive y-Aware InfoNCE loss, that integrates multi-dimensional meta-data, asymptotically optimizes two properties: conditional alignment and global uniformity. Similarly to [Wang, 2020], conditional alignment means that similar samples should have similar features, but conditionally on the meta-data. Instead, global uniformity means that the (normalized) features should be uniformly distributed on the unit hyper-sphere, independently of the meta-data. Here, we propose to define conditional uniformity, relying on the meta-data, that repel only samples with dissimilar meta-data. We show that direct optimization of both conditional alignment and uniformity improves the representations, in terms of linear evaluation, on both CIFAR-100 and a brain MRI dataset.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/16/2021

Contrastive Learning with Continuous Proxy Meta-Data for 3D MRI Classification

Traditional supervised learning with deep neural networks requires a tre...
research
03/08/2022

Contrastive Conditional Neural Processes

Conditional Neural Processes (CNPs) bridge neural networks with probabil...
research
07/17/2021

Lesion-based Contrastive Learning for Diabetic Retinopathy Grading from Fundus Images

Manually annotating medical images is extremely expensive, especially fo...
research
09/16/2023

GCL: Gradient-Guided Contrastive Learning for Medical Image Segmentation with Multi-Perspective Meta Labels

Since annotating medical images for segmentation tasks commonly incurs e...
research
05/28/2023

Whitening-based Contrastive Learning of Sentence Embeddings

This paper presents a whitening-based contrastive learning method for se...
research
05/01/2023

A Simplified Framework for Contrastive Learning for Node Representations

Contrastive learning has recently established itself as a powerful self-...

Please sign up or login with your details

Forgot password? Click here to reset