Learning Domain-Invariant Features for Out-of-Context News Detection

TL;DR

This paper introduces ConDA-TTA, a novel method for detecting out-of-context news across unlabeled domains by learning domain-invariant features through contrastive learning, MMD, and test-time adaptation, improving detection accuracy.

Contribution

It proposes a new domain adaptive out-of-context news detection method combining contrastive learning, MMD, and test-time adaptation for unlabeled domains.

Findings

Outperforms baselines in domain adaptation settings.

Achieves up to 2.93% higher F1 score.

Enhances out-of-context news detection accuracy.

Abstract

Out-of-context news is a common type of misinformation on online media platforms. This involves posting a caption, alongside a mismatched news image. Existing out-of-context news detection models only consider the scenario where pre-labeled data is available for each domain, failing to address the out-of-context news detection on unlabeled domains (e.g. news topics or agencies). In this work, we therefore focus on domain adaptive out-of-context news detection. In order to effectively adapt the detection model to unlabeled news topics or agencies, we propose ConDA-TTA (Contrastive Domain Adaptation with Test-Time Adaptation) which applies contrastive learning and maximum mean discrepancy (MMD) to learn domain-invariant features. In addition, we leverage test-time target domain statistics to further assist domain adaptation. Experimental results show that our approach outperforms baselines in most domain adaptation settings on two public datasets, by as much as 2.93% in F1 and 2.08% in accuracy.