Information Maximization for Long-Tailed Semi-Supervised Domain Generalization
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908873772761088 |
|---|---|
| author | Fillioux, Leo Chakraborty, Omprakash Gopée, Quentin Marza, Pierre Cournède, Paul-Henry Christodoulidis, Stergios Vakalopoulou, Maria Ayed, Ismail Ben Dolz, Jose |
| author_facet | Fillioux, Leo Chakraborty, Omprakash Gopée, Quentin Marza, Pierre Cournède, Paul-Henry Christodoulidis, Stergios Vakalopoulou, Maria Ayed, Ismail Ben Dolz, Jose |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_08434 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Information Maximization for Long-Tailed Semi-Supervised Domain Generalization Fillioux, Leo Chakraborty, Omprakash Gopée, Quentin Marza, Pierre Cournède, Paul-Henry Christodoulidis, Stergios Vakalopoulou, Maria Ayed, Ismail Ben Dolz, Jose Computer Vision and Pattern Recognition 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. |
| title | Information Maximization for Long-Tailed Semi-Supervised Domain Generalization |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.08434 |