Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization

TL;DR

This paper introduces a novel domain-guided weight modulation technique for semi-supervised domain generalization, improving pseudo-label accuracy and model robustness across unseen domains with limited labeled data.

Contribution

The authors propose a domain-aware weight modulation method that retains domain-specific classifier features, enhancing semi-supervised domain generalization performance.

Findings

Significant performance gains over SSL baselines on six datasets.

Effective pseudo-label generation under various domain shifts.

Method is compatible with different SSL frameworks.

Abstract

Unarguably, deep learning models capable of generalizing to unseen domain data while leveraging a few labels are of great practical significance due to low developmental costs. In search of this endeavor, we study the challenging problem of semi-supervised domain generalization (SSDG), where the goal is to learn a domain-generalizable model while using only a small fraction of labeled data and a relatively large fraction of unlabeled data. Domain generalization (DG) methods show subpar performance under the SSDG setting, whereas semi-supervised learning (SSL) methods demonstrate relatively better performance, however, they are considerably poor compared to the fully-supervised DG methods. Towards handling this new, but challenging problem of SSDG, we propose a novel method that can facilitate the generation of accurate pseudo-labels under various domain shifts. This is accomplished by retaining the domain-level specialism in the classifier during training corresponding to each source domain. Specifically, we first create domain-level information vectors on the fly which are then utilized to learn a domain-aware mask for modulating the classifier's weights. We provide a mathematical interpretation for the effect of this modulation procedure on both pseudo-labeling and model training. Our method is plug-and-play and can be readily applied to different SSL baselines for SSDG. Extensive experiments on six challenging datasets in two different SSDG settings show that our method provides visible gains over the various strong SSL-based SSDG baselines.