Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancement

• URL: http://arxiv.org/abs/2506.16728v1
• Date: Fri, 20 Jun 2025 03:52:36 GMT
• Title: Few-Shot Generalized Category Discovery With Retrieval-Guided Decision Boundary Enhancement
• Authors: Yunhan Ren, Feng Luo, Siyu Huang,
• Abstract summary: We introduce the task of Few-shot Generalized Category Discovery (FSGCD)<n>Our framework is designed to learn the decision boundaries of known categories and transfer these boundaries to unknown categories.<n> Experimental results demonstrate that our proposed method outperforms existing methods on six public GCD benchmarks.
• Score: 11.716434502665624
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While existing Generalized Category Discovery (GCD) models have achieved significant success, their performance with limited labeled samples and a small number of known categories remains largely unexplored. In this work, we introduce the task of Few-shot Generalized Category Discovery (FSGCD), aiming to achieve competitive performance in GCD tasks under conditions of known information scarcity. To tackle this challenge, we propose a decision boundary enhancement framework with affinity-based retrieval. Our framework is designed to learn the decision boundaries of known categories and transfer these boundaries to unknown categories. First, we use a decision boundary pre-training module to mitigate the overfitting of pre-trained information on known category boundaries and improve the learning of these decision boundaries using labeled samples. Second, we implement a two-stage retrieval-guided decision boundary optimization strategy. Specifically, this strategy further enhances the severely limited known boundaries by using affinity-retrieved pseudo-labeled samples. Then, these refined boundaries are applied to unknown clusters via guidance from affinity-based feature retrieval. Experimental results demonstrate that our proposed method outperforms existing methods on six public GCD benchmarks under the FSGCD setting. The codes are available at: https://github.com/Ryh1218/FSGCD

Related papers

• Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery [64.83837781610907]
  We investigate the online identification of newly arriving stream data that may belong to both known and unknown categories.<n>Existing OCD methods are devoted to fully mining transferable knowledge from only labeled data.<n>We propose a diffusion-based OCD framework, dubbed DiffGRE, which integrates attribute-composition generation, Refinement, and supervised recognition.
  arXiv  Detail & Related papers  (2025-07-05T14:20:49Z)
• BoundMatch: Boundary detection applied to semi-supervised segmentation for urban-driving scenes [6.236890292833387]
  Semi-supervised semantic segmentation (SS-SS) aims to mitigate the heavy annotation burden of dense pixel labeling.<n>In this paper, we propose BoundMatch, a novel multi-task SS-SS framework that integrates semantic boundary detection into a teacher-student consistency regularization pipeline.<n>Our core mechanism, Boundary Consistency Regularized Multi-Task Learning, enforces prediction agreement between teacher and student models on both segmentation masks and detailed semantic boundaries.
  arXiv  Detail & Related papers  (2025-03-30T17:02:26Z)
• Freeze and Cluster: A Simple Baseline for Rehearsal-Free Continual Category Discovery [13.68907640197364]
  This paper addresses the problem of Rehearsal-Free Continual Category Discovery (RF-CCD)<n>RF-CCD focuses on continuously identifying novel class by leveraging knowledge from labeled data.<n>Previous approaches have struggled to effectively integrate advanced techniques from both domains.
  arXiv  Detail & Related papers  (2025-03-12T06:46:32Z)
• Multi-Granularity Open Intent Classification via Adaptive Granular-Ball Decision Boundary [22.669965275069313]
  We propose a Multi-granularity Open intent classification method via adaptive Granular-Ball decision boundary (MOGB)<n>Our MOGB method consists of two modules: representation learning and decision boundary acquiring.<n>This involves iteratively alternating between adaptive granular-ball clustering and nearest sub-centroid classification to capture fine-grained semantic structures within known intent classes.
  arXiv  Detail & Related papers  (2024-12-18T06:42:19Z)
• Cross-Domain Few-Shot Segmentation via Iterative Support-Query Correspondence Mining [81.09446228688559]
  Cross-Domain Few-Shots (CD-FSS) poses the challenge of segmenting novel categories from a distinct domain using only limited exemplars. We propose a novel cross-domain fine-tuning strategy that addresses the challenging CD-FSS tasks.
  arXiv  Detail & Related papers  (2024-01-16T14:45:41Z)
• Generalized Categories Discovery for Long-tailed Recognition [8.69033435074757]
  Generalized Class Discovery plays a pivotal role in discerning both known and unknown categories from unlabeled datasets. Our research endeavors to bridge this disconnect by focusing on the long-tailed Generalized Category Discovery (Long-tailed GCD) paradigm. In response to the unique challenges posed by Long-tailed GCD, we present a robust methodology anchored in two strategic regularizations.
  arXiv  Detail & Related papers  (2023-12-04T09:21:30Z)
• Activate and Reject: Towards Safe Domain Generalization under Category Shift [71.95548187205736]
  We study a practical problem of Domain Generalization under Category Shift (DGCS) It aims to simultaneously detect unknown-class samples and classify known-class samples in the target domains. Compared to prior DG works, we face two new challenges: 1) how to learn the concept of unknown'' during training with only source known-class samples, and 2) how to adapt the source-trained model to unseen environments.
  arXiv  Detail & Related papers  (2023-10-07T07:53:12Z)
• Temporal Action Localization with Enhanced Instant Discriminability [66.76095239972094]
  Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. We propose a one-stage framework named TriDet to resolve imprecise predictions of action boundaries by existing methods. Experimental results demonstrate the robustness of TriDet and its state-of-the-art performance on multiple TAD datasets.
  arXiv  Detail & Related papers  (2023-09-11T16:17:50Z)
• Automated Imbalanced Classification via Layered Learning [0.734084539365505]
  Applying resampling strategies to balance the class distribution of training instances is a common approach to tackle these problems. Many state-of-the-art methods find instances of interest close to the decision boundary to drive the resampling process. Over-sampling may increase the chance of overfitting by propagating the information contained in instances from the minority class.
  arXiv  Detail & Related papers  (2022-05-05T10:32:24Z)
• MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
  Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition. We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL) In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
  arXiv  Detail & Related papers  (2021-07-23T06:57:08Z)
• DeepStrip: High Resolution Boundary Refinement [60.00241966809684]
  We propose to convert regions of interest into strip images and compute a boundary prediction in the strip domain. To detect the target boundary, we present a framework with two prediction layers. We enforce a matching consistency and C0 continuity regularization to the network to reduce false alarms.
  arXiv  Detail & Related papers  (2020-03-25T22:44:48Z)

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.