HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery

• URL: http://arxiv.org/abs/2510.17188v1
• Date: Mon, 20 Oct 2025 06:08:33 GMT
• Title: HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery
• Abstract summary: Generalized Category Discovery (GCD) aims to classify test-time samples into either seen** -- available during training -- or novel ones, without relying on label supervision.<n>Most existing GCD methods assume simultaneous access to labeled and unlabeled data during training.<n>We propose HIDISC, a hyperbolic representation learning framework that achieves domain and category-level without episodic simulation.
• Score: 21.232375739287
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generalized Category Discovery (GCD) aims to classify test-time samples into either seen categories** -- available during training -- or novel ones, without relying on label supervision. Most existing GCD methods assume simultaneous access to labeled and unlabeled data during training and arising from the same domain, limiting applicability in open-world scenarios involving distribution shifts. Domain Generalization with GCD (DG-GCD) lifts this constraint by requiring models to generalize to unseen domains containing novel categories, without accessing targetdomain data during training. The only prior DG-GCD method, DG2CD-Net, relies on episodic training with multiple synthetic domains and task vector aggregation, incurring high computational cost and error accumulation. We propose HIDISC, a hyperbolic representation learning framework that achieves domain and category-level generalization without episodic simulation. To expose the model to minimal but diverse domain variations, we augment the source domain using GPT-guided diffusion, avoiding overfitting while maintaining efficiency. To structure the representation space, we introduce Tangent CutMix, a curvature-aware interpolation that synthesizes pseudo-novel samples in tangent space, preserving manifold consistency. A unified loss -- combining penalized Busemann alignment, hybrid hyperbolic contrastive regularization, and adaptive outlier repulsion -- **facilitates compact, semantically structured embeddings. A learnable curvature parameter further adapts the geometry to dataset complexity. HIDISC achieves state-of-the-art results on PACS , Office-Home , and DomainNet, consistently outperforming the existing Euclidean and hyperbolic (DG)-GCD baselines.

Related papers

• Generalized Category Discovery in Federated Graph Learning [10.91485241015392]
  Federated Graph Generalized Category Discovery (FGGCD) aims to collaboratively discover novel categories across decentralized graph clients.<n>We propose GCD-FGL, an FGL framework for GCD that integrates a client-side Topology-Reliable Semantic Alignment and Discovery process.<n>Experiments on five real-world graph datasets demonstrate that GCD-FGL consistently outperforms state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-05T08:37:29Z)
• Dual-supervised Asymmetric Co-training for Semi-supervised Medical Domain Generalization [9.633663242642305]
  Semi-supervised domain generalization (SSDG) in medical image segmentation offers a promising solution for generalizing to unseen domains during testing.<n> conventional SSDG methods assume labeled and unlabeled data are available for each source domain in the training set, a condition that is not always met in practice.<n>This paper explores a more practical and challenging scenario, where domain shifts occur between labeled and unlabeled training data.<n>Existing SSDG methods exhibit sub-optimal performance under such domain shifts because of inaccurate pseudolabels.
  arXiv  Detail & Related papers  (2025-09-25T06:13:25Z)
• Hyperbolic Category Discovery [12.654574453480635]
  Generalized Category Discovery (GCD) aims to categorize all images in the unlabelled subset, regardless of whether they belong to known or unknown classes.<n>Hyperbolic framework for learning hierarchy-aware representations and classifiers for GCD is presented.
  arXiv  Detail & Related papers  (2025-04-08T15:12:33Z)
• When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach [29.664356718958803]
  Generalized Class Discovery (GCD) clusters base and novel classes in a target domain using supervision from a source domain with only base classes.<n>We introduce the novel paradigm of Domain Generalization in GCD (DG-GCD), where only source data is available for training.<n>Our solution, DG2CD-Net, aims to construct a domain-independent, discriminative embedding space for GCD.
  arXiv  Detail & Related papers  (2025-03-19T04:48:16Z)
• Towards Cross-domain Few-shot Graph Anomaly Detection [6.732699844225434]
  Cross-domain few-shot graph anomaly detection (GAD) is nontrivial owing to inherent data distribution discrepancies between the source and target domains. We propose a simple and effective framework, termed CDFS-GAD, specifically designed to tackle the aforementioned challenges.
  arXiv  Detail & Related papers  (2024-10-11T08:47:25Z)
• 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)
• Upcycling Models under Domain and Category Shift [95.22147885947732]
  We introduce an innovative global and local clustering learning technique (GLC) We design a novel, adaptive one-vs-all global clustering algorithm to achieve the distinction across different target classes. Remarkably, in the most challenging open-partial-set DA scenario, GLC outperforms UMAD by 14.8% on the VisDA benchmark.
  arXiv  Detail & Related papers  (2023-03-13T13:44:04Z)
• Semantic-Aware Domain Generalized Segmentation [67.49163582961877]
  Deep models trained on source domain lack generalization when evaluated on unseen target domains with different data distributions. We propose a framework including two novel modules: Semantic-Aware Normalization (SAN) and Semantic-Aware Whitening (SAW) Our approach shows significant improvements over existing state-of-the-art on various backbone networks.
  arXiv  Detail & Related papers  (2022-04-02T09:09:59Z)
• 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)
• Towards Uncovering the Intrinsic Data Structures for Unsupervised Domain Adaptation using Structurally Regularized Deep Clustering [119.88565565454378]
  Unsupervised domain adaptation (UDA) is to learn classification models that make predictions for unlabeled data on a target domain. We propose a hybrid model of Structurally Regularized Deep Clustering, which integrates the regularized discriminative clustering of target data with a generative one. Our proposed H-SRDC outperforms all the existing methods under both the inductive and transductive settings.
  arXiv  Detail & Related papers  (2020-12-08T08:52:00Z)
• Simultaneous Semantic Alignment Network for Heterogeneous Domain Adaptation [67.37606333193357]
  We propose aSimultaneous Semantic Alignment Network (SSAN) to simultaneously exploit correlations among categories and align the centroids for each category across domains. By leveraging target pseudo-labels, a robust triplet-centroid alignment mechanism is explicitly applied to align feature representations for each category. Experiments on various HDA tasks across text-to-image, image-to-image and text-to-text successfully validate the superiority of our SSAN against state-of-the-art HDA methods.
  arXiv  Detail & Related papers  (2020-08-04T16:20:37Z)

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.