Information Maximization for Long-Tailed Semi-Supervised Domain Generalization

ArXi:2603.08434v1 Announce Type: new Semi-supervised domain generalization (SSDG) has recently emerged as an appealing alternative to tackle domain generalization when labeled data is scarce but unlabeled samples across domains are abundant. In this work, we identify an important limitation that hampers the deployment of state-of-the-art methods on challenging but practical scenarios. In particular, state-of-the-art SSDG severely suffers in the presence of long-tailed class distributions, an arguably common situation in real-world settings.