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

2025/06/20 by Ren, Yunhan, Luo, Feng, Huang, Siyu
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Text and Document Classification Technologies #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2506.16728

openalex publication_date 2025/06/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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

Citations

• Contrastive Mean-Shift Learning for Generalized Category Discovery
• SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
• Transfer and Alignment Network for Generalized Category Discovery
• Towards Open Vocabulary Learning: A Survey
• Learning Semi-supervised Gaussian Mixture Models for Generalized Category Discovery
• XCon: Learning with Experts for Fine-grained Category Discovery
• Few-shot Open-set Recognition Using Background as Unknowns
• AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
• Open-Set Recognition: a Good Closed-Set Classifier is All You Need?
• A Unified Objective for Novel Class Discovery
• Review on Convolutional Neural Network (CNN) Applied to Plant Leaf Disease Classification
• Novel Visual Category Discovery with Dual Ranking Statistics and Mutual Knowledge Distillation
• Emerging Properties in Self-Supervised Vision Transformers
• Learning Placeholders for Open-Set Recognition
• Few-shot Open-set Recognition by Transformation Consistency
• Reproducibility Report: La-MAML: Look-ahead Meta Learning for Continual Learning
• Few-Shot Open-Set Recognition using Meta-Learning
• iTAML: An Incremental Task-Agnostic Meta-learning Approach
• AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning
• A Simple Framework for Contrastive Learning of Visual Representations
• Automatically Discovering and Learning New Visual Categories with Ranking Statistics
• Learning to Discover Novel Visual Categories via Deep Transfer Clustering
• The Herbarium Challenge 2019 Dataset
• Image Deformation Meta-Networks for One-Shot Learning
• Few-Shot Learning via Saliency-guided Hallucination of Samples
• LaSO: Label-Set Operations networks for multi-label few-shot learning
• Task-Agnostic Meta-Learning for Few-shot Learning
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• ImageNet Large Scale Visual Recognition Challenge
• ImageNet Large Scale Visual Recognition Challenge

Related

• Prior-Constrained Association Learning for Fine-Grained Generalized Category Discovery
• Sharpness-aware Dynamic Anchor Selection for Generalized Category Discovery
• GLEAN: Active Generalized Category Discovery with Diverse LLM Feedback
• Few-shot Novel Category Discovery
• Solving the Catastrophic Forgetting Problem in Generalized Category Discovery