Related papers: GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery

GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery

URL: http://arxiv.org/abs/2602.19872v1
Date: Mon, 23 Feb 2026 14:15:56 GMT
Title: GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery
Authors: Jizhou Han, Chenhao Ding, SongLin Dong, Yuhang He, Shaokun Wang, Qiang Wang, Yihong Gong,
Abstract summary: Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data.<n>We propose GOAL, a unified framework that introduces a fixed Equiangular Tight Frame (ETF) classifier to impose a consistent geometric structure throughout learning.
Score: 48.78384108448773
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Continual Generalized Category Discovery (C-GCD) requires identifying novel classes from unlabeled data while retaining knowledge of known classes over time. Existing methods typically update classifier weights dynamically, resulting in forgetting and inconsistent feature alignment. We propose GOAL, a unified framework that introduces a fixed Equiangular Tight Frame (ETF) classifier to impose a consistent geometric structure throughout learning. GOAL conducts supervised alignment for labeled samples and confidence-guided alignment for novel samples, enabling stable integration of new classes without disrupting old ones. Experiments on four benchmarks show that GOAL outperforms the prior method Happy, reducing forgetting by 16.1% and boosting novel class discovery by 3.2%, establishing a strong solution for long-horizon continual discovery.

Related papers

Reliable Active Learning from Unreliable Labels via Neural Collapse Geometry [5.1511135538176]
Active Learning (AL) promises to reduce annotation cost by prioritizing informative samples, yet its reliability is undermined when labels are noisy or when the data distribution shifts.<n>We propose Active Learning via Neural Collapse Geometry (NCAL-R), a framework that leverages the emergent geometric regularities of deep networks to counteract unreliable supervision.
arXiv Detail & Related papers (2025-10-10T17:50:31Z)
Consistent Supervised-Unsupervised Alignment for Generalized Category Discovery [49.67913741459179]
Generalized Category Discovery (GCD) focuses on classifying known categories while simultaneously discovering novel categories from unlabeled data.<n>Previous GCD methods face challenges due to inconsistent optimization objectives and category confusion.<n>We propose the Neural Collapse-inspired Generalized Category Discovery (NC-GCD) framework.
arXiv Detail & Related papers (2025-07-07T07:34:41Z)
CLIMB-3D: Continual Learning for Imbalanced 3D Instance Segmentation [67.36817440834251]
We propose a unified framework for textbfCLass-incremental textbfImbalance-aware textbf3DIS.<n>Our approach achieves state-of-the-art results, surpassing prior work by up to 16.76% mAP for instance segmentation and approximately 30% mIoU for semantic segmentation.
arXiv Detail & Related papers (2025-02-24T18:58:58Z)
Generalized Class Discovery in Instance Segmentation [7.400926717561454]
We propose an instance-wise temperature assignment (ITA) method for contrastive learning and class-wise reliability criteria for pseudo-labels.<n>We evaluate our proposed method by conducting experiments on two settings: COCO$_half$ + LVIS and LVIS + Visual Genome.
arXiv Detail & Related papers (2025-02-12T06:26:05Z)
Solving the Catastrophic Forgetting Problem in Generalized Category Discovery [46.63232918739251]
Generalized Category Discovery (GCD) aims to identify a mix of known and novel categories within unlabeled data sets.<n>Recent state-of-the-art method SimGCD transfers the knowledge from known-class data to the learning of novel classes through debiased learning.<n>We propose a novel learning approach, LegoGCD, which is seamlessly integrated into previous methods to enhance the discrimination of novel classes.
arXiv Detail & Related papers (2025-01-09T14:31:54Z)
Happy: A Debiased Learning Framework for Continual Generalized Category Discovery [54.54153155039062]
This paper explores the underexplored task of Continual Generalized Category Discovery (C-GCD) C-GCD aims to incrementally discover new classes from unlabeled data while maintaining the ability to recognize previously learned classes. We introduce a debiased learning framework, namely Happy, characterized by Hardness-aware prototype sampling and soft entropy regularization.
arXiv Detail & Related papers (2024-10-09T04:18:51Z)
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)
Parametric Classification for Generalized Category Discovery: A Baseline Study [70.73212959385387]
Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples. We investigate the failure of parametric classifiers, verify the effectiveness of previous design choices when high-quality supervision is available, and identify unreliable pseudo-labels as a key problem. We propose a simple yet effective parametric classification method that benefits from entropy regularisation, achieves state-of-the-art performance on multiple GCD benchmarks and shows strong robustness to unknown class numbers.
arXiv Detail & Related papers (2022-11-21T18:47:11Z)

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