DeepAI AI Chat
Log In Sign Up

Robust Contrastive Learning against Noisy Views

by   Ching-Yao Chuang, et al.

Contrastive learning relies on an assumption that positive pairs contain related views, e.g., patches of an image or co-occurring multimodal signals of a video, that share certain underlying information about an instance. But what if this assumption is violated? The literature suggests that contrastive learning produces suboptimal representations in the presence of noisy views, e.g., false positive pairs with no apparent shared information. In this work, we propose a new contrastive loss function that is robust against noisy views. We provide rigorous theoretical justifications by showing connections to robust symmetric losses for noisy binary classification and by establishing a new contrastive bound for mutual information maximization based on the Wasserstein distance measure. The proposed loss is completely modality-agnostic and a simple drop-in replacement for the InfoNCE loss, which makes it easy to apply to existing contrastive frameworks. We show that our approach provides consistent improvements over the state-of-the-art on image, video, and graph contrastive learning benchmarks that exhibit a variety of real-world noise patterns.


page 1

page 4

page 7

page 20


On Mutual Information in Contrastive Learning for Visual Representations

In recent years, several unsupervised, "contrastive" learning algorithms...

Conditional Negative Sampling for Contrastive Learning of Visual Representations

Recent methods for learning unsupervised visual representations, dubbed ...

Learning Invariant Representations using Inverse Contrastive Loss

Learning invariant representations is a critical first step in a number ...

An Adaptive Contrastive Learning Model for Spike Sorting

Brain-computer interfaces (BCIs), is ways for electronic devices to comm...

Intriguing Properties of Contrastive Losses

Contrastive loss and its variants have become very popular recently for ...

Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives

This paper introduces Ranking Info Noise Contrastive Estimation (RINCE),...

Understanding Multimodal Contrastive Learning and Incorporating Unpaired Data

Language-supervised vision models have recently attracted great attentio...

Code Repositories


Code for Robust Contrastive Learning against Noisy Views

view repo