# Information Maximization for Long-Tailed Semi-Supervised Domain Generalization

arXiv: https://arxiv.org/abs/2603.08434 · HTML: https://mlsanity.com/paper/2603.08434/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Natural Adversarial Examples](https://mlsanity.com/paper/1907.07174/) (2019)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [A Baseline for Few-Shot Image Classification](https://mlsanity.com/paper/1909.02729/) (2019)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?](https://mlsanity.com/paper/2012.06166/) (2020)
- [Domain Generalization for Medical Imaging Classification with Linear-Dependency Regularization](https://mlsanity.com/paper/2009.12829/) (2020)
- [Causality-inspired Single-source Domain Generalization for Medical Image Segmentation](https://mlsanity.com/paper/2111.12525/) (2021)
- [A Foundation Language-Image Model of the Retina (FLAIR): Encoding Expert Knowledge in Text Supervision](https://mlsanity.com/paper/2308.07898/) (2023)
- [Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy](https://mlsanity.com/paper/1710.01711/) (2017)
- [Semi-Supervised Domain Generalization with Stochastic StyleMatch](https://mlsanity.com/paper/2106.00592/) (2021)
- [Parametric Information Maximization for Generalized Category Discovery](https://mlsanity.com/paper/2212.00334/) (2022)
- [Deep clustering: On the link between discriminative models and K-means](https://mlsanity.com/paper/1810.04246/) (2018)
- [Realistic Evaluation of Transductive Few-Shot Learning](https://mlsanity.com/paper/2204.11181/) (2022)
- [A Strong Baseline for Generalized Few-Shot Semantic Segmentation](https://mlsanity.com/paper/2211.14126/) (2022)
- [Towards Generalizing to Unseen Domains with Few Labels](https://mlsanity.com/paper/2403.11674/) (2024)
- [Generalised Mutual Information for Discriminative Clustering](https://mlsanity.com/paper/2210.06300/) (2022)
- [Domain-Guided Weight Modulation for Semi-Supervised Domain Generalization](https://mlsanity.com/paper/2409.03509/) (2024)
- [Dual-supervised Asymmetric Co-training for Semi-supervised Medical Domain Generalization](https://mlsanity.com/paper/2509.20785/) (2025)

## Abstract (arXiv)

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 more 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. To alleviate this limitation, we propose IMaX, a simple yet effective objective based on the well-known InfoMax principle adapted to the SSDG scenario, where the Mutual Information (MI) between the learned features and latent labels is maximized, constrained by the supervision from the labeled samples. Our formulation integrates an α-entropic objective, which mitigates the class-balance bias encoded in the standard marginal entropy term of the MI, thereby better handling arbitrary class distributions. IMaX can be seamlessly plugged into recent state-of-the-art SSDG, consistently enhancing their performance, as demonstrated empirically across two different image modalities.