Towards Generalizing to Unseen Domains with Few Labels

TL;DR

This paper introduces a novel semi-supervised domain generalization method that leverages unlabeled data to improve model robustness across unseen domains, outperforming existing approaches.

Contribution

The paper proposes a feature conformity technique and a semantics alignment loss to enhance semi-supervised domain generalization without extra parameters.

Findings

Consistent improvements across five benchmarks.

Significant gains with multiple SSL baselines.

Method is plug-and-play and easy to integrate.

Abstract

We approach the challenge of addressing semi-supervised domain generalization (SSDG). Specifically, our aim is to obtain a model that learns domain-generalizable features by leveraging a limited subset of labelled data alongside a substantially larger pool of unlabeled data. Existing domain generalization (DG) methods which are unable to exploit unlabeled data perform poorly compared to semi-supervised learning (SSL) methods under SSDG setting. Nevertheless, SSL methods have considerable room for performance improvement when compared to fully-supervised DG training. To tackle this underexplored, yet highly practical problem of SSDG, we make the following core contributions. First, we propose a feature-based conformity technique that matches the posterior distributions from the feature space with the pseudo-label from the model's output space. Second, we develop a semantics alignment loss to learn semantically-compatible representations by regularizing the semantic structure in the feature space. Our method is plug-and-play and can be readily integrated with different SSL-based SSDG baselines without introducing any additional parameters. Extensive experimental results across five challenging DG benchmarks with four strong SSL baselines suggest that our method provides consistent and notable gains in two different SSDG settings.