Information Maximization for Long-Tailed Semi-Supervised Domain Generalization

• URL: http://arxiv.org/abs/2603.08434v1
• Date: Mon, 09 Mar 2026 14:32:10 GMT
• Title: Information Maximization for Long-Tailed Semi-Supervised Domain Generalization
• Abstract summary: Semi-supervised domain generalization has emerged as an appealing alternative to tackle domain generalization when labeled data is scarce but unlabeled samples are abundant.<n>We propose IMaX, a simple yet effective objective based on the well-known InfoMax principle adapted to the SSDG scenario.<n>Our formulation integrates an -entropic objective, which mitigates the class-balance bias encoded in the standard marginal entropy term of the MI, thereby better handling arbitrary class distributions.
• Score: 30.470443666380365
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• SemAlign: Language Guided Semi-supervised Domain Generalization [0.6449696427299687]
  Semi-supervised Domain Generalization addresses the challenge of generalizing to unseen target domains with limited labeled data.<n>We show that the SSDG literature's excessive focus on PL accuracy, without consideration for maximum data utilization during training, limits potential performance improvements.<n>We propose a novel approach to the SSDG problem by aligning the intermediate features of our model with the semantically rich and generalized feature space of a Vision Language Model.
  arXiv  Detail & Related papers  (2026-01-16T19:16:45Z)
• Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization [26.836715714223796]
  Unsupervised Domain Generalization (UDG) task has been proposed to enhance the generalization of models trained with prevalent unsupervised learning techniques.<n>We formalize UDG as the task of learning a Minimal Sufficient Semantic Representation (MS-UDG)<n>MS-UDG sets a new state-of-the-art on popular unsupervised domain-generalization benchmarks, consistently outperforming existing SSL and UDG methods.
  arXiv  Detail & Related papers  (2025-09-19T09:22:19Z)
• Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection [53.137651284042434]
  Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples limits the effectiveness of existing methods.<n>We propose Generate grained Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework.<n>GAA generates realistic, diverse, and semantically aligned anomalies using only a small number of samples.
  arXiv  Detail & Related papers  (2025-07-13T12:56:59Z)
• FedSemiDG: Domain Generalized Federated Semi-supervised Medical Image Segmentation [19.87797382888023]
  Medical image segmentation is challenging due to the diversity of medical images and the lack of labeled data.<n>We present a novel framework, Federated Generalization-Aware SemiSupervised Learning (FGASL), to address the challenges in FedSemiDG.<n>Our method significantly outperforms state-of-the-art FSSL and domain generalization approaches, achieving robust generalization on unseen domains.
  arXiv  Detail & Related papers  (2025-01-13T14:54:49Z)
• CAT: Class Aware Adaptive Thresholding for Semi-Supervised Domain Generalization [0.989976359821412]
  Domain Generalization seeks to transfer knowledge from source domains to unseen target domains, even in the presence of domain shifts.<n>We propose a novel method, CAT, which leverages semi-supervised learning with limited labeled data to achieve competitive generalization performance under domain shifts.<n>Our approach uses flexible thresholding to generate high-quality pseudo-labels with higher class diversity while refining noisy pseudo-labels to improve their reliability.
  arXiv  Detail & Related papers  (2024-12-11T15:47:01Z)
• DGMamba: Domain Generalization via Generalized State Space Model [80.82253601531164]
  Domain generalization(DG) aims at solving distribution shift problems in various scenes. Mamba, as an emerging state space model (SSM), possesses superior linear complexity and global receptive fields. We propose a novel framework for DG, named DGMamba, that excels in strong generalizability toward unseen domains.
  arXiv  Detail & Related papers  (2024-04-11T14:35:59Z)
• META: Mimicking Embedding via oThers' Aggregation for Generalizable Person Re-identification [68.39849081353704]
  Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time. This paper presents a new approach called Mimicking Embedding via oThers' Aggregation (META) for DG ReID.
  arXiv  Detail & Related papers  (2021-12-16T08:06:50Z)
• Semi-Supervised Domain Generalization with Stochastic StyleMatch [90.98288822165482]
  In real-world applications, we might have only a few labels available from each source domain due to high annotation cost. In this work, we investigate semi-supervised domain generalization, a more realistic and practical setting. Our proposed approach, StyleMatch, is inspired by FixMatch, a state-of-the-art semi-supervised learning method based on pseudo-labeling.
  arXiv  Detail & Related papers  (2021-06-01T16:00:08Z)
• Generalizable Representation Learning for Mixture Domain Face Anti-Spoofing [53.82826073959756]
  Face anti-spoofing approach based on domain generalization(DG) has drawn growing attention due to its robustness forunseen scenarios. We propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels. To overcome the limitation, we propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels.
  arXiv  Detail & Related papers  (2021-05-06T06:04:59Z)
• Learning Invariant Representations and Risks for Semi-supervised Domain Adaptation [109.73983088432364]
  We propose the first method that aims to simultaneously learn invariant representations and risks under the setting of semi-supervised domain adaptation (Semi-DA) We introduce the LIRR algorithm for jointly textbfLearning textbfInvariant textbfRepresentations and textbfRisks.
  arXiv  Detail & Related papers  (2020-10-09T15:42:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.