从贝叶斯视角解决持续学习中的遗忘问题，提升新旧类别识别准确率。
Continual Generalized Category Discovery: Learning and Forgetting from a Bayesian Perspective
- 基于变分贝叶斯框架，动态对齐类间协方差分布
- 在标准数据集上最终会话准确率提升15.21%
- 适用于标签极少、在线阶段长的严苛场景
持续广义类别发现（C-GCD）面临核心挑战：从无标签数据流中增量学习新类别，同时保留旧类别知识。现有方法在新旧类别混合的无标签数据下易出现灾难性遗忘。本文通过贝叶斯视角分析遗忘机制，发现旧类与新类之间的协方差错配是性能下降主因。据此提出变分贝叶斯持续广义类别发现（VB-CGCD），融合变分推断与协方差感知的最近类均值分类。该方法通过随机变分更新自适应对齐类分布，并抑制伪标签噪声。实验表明，VB-CGCD在标准基准上最终会话整体准确率提升15.21%。我们还构建了新基准，仅10%标签且在线阶段更长，其最终准确率达67.86%，显著优于当前最优方法（38.55%），验证了模型在多样场景下的鲁棒性。代码已开源。
原文摘要 · Abstract (English)
Continual Generalized Category Discovery (C-GCD) faces a critical challenge: incrementally learning new classes from unlabeled data streams while preserving knowledge of old classes. Existing methods struggle with catastrophic forgetting, especially when unlabeled data mixes known and novel categories. We address this by analyzing C-GCD's forgetting dynamics through a Bayesian lens, revealing that covariance misalignment between old and new classes drives performance degradation. Building on this insight, we propose Variational Bayes C-GCD (VB-CGCD), a novel framework that integrates variational inference with covariance-aware nearest-class-mean classification. VB-CGCD adaptively aligns class distributions while suppressing pseudo-label noise via stochastic variational updates. Experiments show VB-CGCD surpasses prior art by +15.21% with the overall accuracy in the final session on standard benchmarks. We also introduce a new challenging benchmark with only 10% labeled data and extended online phases, VB-CGCD achieves a 67.86% final accuracy, significantly higher than state-of-the-art (38.55%), demonstrating its robust applicability across diverse scenarios. Code is available at: https://github.com/daihao42/VB-CGCD
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。