FOCUS: Bridging Fine-Grained Recognition and Open-World Discovery across Domains

• URL: http://arxiv.org/abs/2603.14240v1
• Date: Sun, 15 Mar 2026 06:25:18 GMT
• Title: FOCUS: Bridging Fine-Grained Recognition and Open-World Discovery across Domains
• Abstract summary: We introduce the first unified framework for *Fine-Grained Domain-Generalized Generalized Category Discovery (FG-DG-GCD)<n>FG-GCD learns only from labeled source data and must both recognize known classes and discover novel ones in unseen, unlabeled target domains.<n>We propose FoCUS, a single-stage framework that combines *Domain-Consistent Parts Discovery* (DCPD) for geometry-stable part reasoning with *Uncertainty-Aware Feature Augmentation* (UFA) for confidence-calibrated feature regularization.
• Score: 23.499158058522344
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce the first unified framework for *Fine-Grained Domain-Generalized Generalized Category Discovery* (FG-DG-GCD), bringing open-world recognition closer to real-world deployment under domain shift. Unlike conventional GCD, which assumes labeled and unlabeled data come from the same distribution, DG-GCD learns only from labeled source data and must both recognize known classes and discover novel ones in unseen, unlabeled target domains. This problem is especially challenging in fine-grained settings, where subtle inter-class differences and large intra-class variation make domain generalization significantly harder. To support systematic evaluation, we establish the first *FG-DG-GCD benchmarks* by creating identity-preserving *painting* and *sketch* domains for CUB-200-2011, Stanford Cars, and FGVC-Aircraft using controlled diffusion-adapter stylization. On top of this ,we propose FoCUS, a single-stage framework that combines *Domain-Consistent Parts Discovery* (DCPD) for geometry-stable part reasoning with *Uncertainty-Aware Feature Augmentation* (UFA) for confidence-calibrated feature regularization through uncertainty-guided perturbations. Extensive experiments show that FoCUS outperforms strong GCD, FG-GCD, and DG-GCD baselines by **3.28%**, **9.68%**, and **2.07%**, respectively, in clustering accuracy on the proposed benchmarks. It also remains competitive on coarse-grained DG-GCD tasks while achieving nearly **3x** higher computational efficiency than the current state of the art. ^[Code and datasets will be released upon acceptance.]

Related papers

• CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category Discovery [16.721682363090043]
  CloSeR injects Closed-Set knowledge into Generalized Category Discovery training.<n>Experiments with DINO and DINOv2 backbones on six benchmarks show consistent gains over GCD baselines.
  arXiv  Detail & Related papers  (2026-08-26T12:10:54Z)
• HIDISC: A Hyperbolic Framework for Domain Generalization with Generalized Category Discovery [21.232375739287]
  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.
  arXiv  Detail & Related papers  (2025-10-20T06:08:33Z)
• Generative Classifier for Domain Generalization [84.92088101715116]
  Domain generalization aims to the generalizability of computer vision models toward distribution shifts.<n>We propose Generative-driven Domain Generalization (GCDG)<n>GCDG consists of three key modules: Heterogeneity Learning(HLC), Spurious Correlation(SCB), and Diverse Component Balancing(DCB)
  arXiv  Detail & Related papers  (2025-04-03T04:38:33Z)
• 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)
• Disentangling Masked Autoencoders for Unsupervised Domain Generalization [57.56744870106124]
  Unsupervised domain generalization is fast gaining attention but is still far from well-studied. Disentangled Masked Auto (DisMAE) aims to discover the disentangled representations that faithfully reveal intrinsic features. DisMAE co-trains the asymmetric dual-branch architecture with semantic and lightweight variation encoders.
  arXiv  Detail & Related papers  (2024-07-10T11:11:36Z)
• Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation [86.61336696914447]
  We dub our approach "Invariant CONsistency learning" (ICON) We propose to make the U in Unsupervised DA matter by giving equal status to the two domains. ICON achieves the state-of-the-art performance on the classic UDA benchmarks: Office-Home and VisDA-2017, and outperforms all the conventional methods on the challenging WILDS 2.0 benchmark.
  arXiv  Detail & Related papers  (2023-09-22T09:43:32Z)
• 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)
• Federated Unsupervised Domain Adaptation for Face Recognition [26.336693850812118]
  We propose federated unsupervised domain adaptation for face recognition, FedFR. For unlabeled data in the target domain, we enhance a clustering algorithm with distance constrain to improve the quality of predicted pseudo labels. We also propose a new domain constraint loss to regularize source domain training in federated learning.
  arXiv  Detail & Related papers  (2022-04-09T04:02:03Z)
• Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning [85.6386289476598]
  We develop a novel adversarial graph representation adaptation (AGRA) framework for cross-domain holistic-local feature co-adaptation. We conduct extensive and fair evaluations on several popular benchmarks and show that the proposed AGRA framework outperforms previous state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-08-03T15:00:31Z)
• Mind the Gap: Enlarging the Domain Gap in Open Set Domain Adaptation [65.38975706997088]
  Open set domain adaptation (OSDA) assumes the presence of unknown classes in the target domain. We show that existing state-of-the-art methods suffer a considerable performance drop in the presence of larger domain gaps. We propose a novel framework to specifically address the larger domain gaps.
  arXiv  Detail & Related papers  (2020-03-08T14:20:24Z)

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.