Generalized Class Discovery (GCD) aims to dynamically assign labels to unlabelled data partially based on knowledge learned from labelled data, where the unlabelled data may come from known or novel classes. The prevailing approach generally involves clustering across all data and learning conceptions by prototypical contrastive learning. However, existing methods largely hinge on the performance of clustering algorithms and are thus subject to their inherent limitations. Firstly, the estimated cluster number is often smaller than the ground truth, making the existing methods suffer from the lack of prototypes for comprehensive conception learning. To address this issue, we propose an adaptive probing mechanism that introduces learnable potential prototypes to expand cluster prototypes (centers). As there is no ground truth for the potential prototype, we develop a self-supervised prototype learning framework to optimize the potential prototype in an end-to-end fashion. Secondly, clustering is computationally intensive, and the conventional strategy of clustering both labelled and unlabelled instances exacerbates this issue. To counteract this inefficiency, we opt to cluster only the unlabelled instances and subsequently expand the cluster prototypes with our introduced potential prototypes to fast explore novel classes. Despite the simplicity of our proposed method, extensive empirical analysis on a wide range of datasets confirms that our method consistently delivers state-of-the-art results. Specifically, our method surpasses the nearest competitor by a significant margin of \textbf{9.7}$\%$ within the Stanford Cars dataset and \textbf{12$\times$} clustering efficiency within the Herbarium 19 dataset. We will make the code and checkpoints publicly available at \url{https://github.com/xjtuYW/PNP.git}.

翻译：广义类发现（GCD）旨在基于从标注数据中习得的知识，动态地为未标注数据分配标签，其中未标注数据可能来自已知或新类别。当前主流方法通常涉及对所有数据进行聚类，并通过原型对比学习来构建概念。然而，现有方法高度依赖聚类算法的性能，因此受限于其固有缺陷。首先，估计的聚类数通常小于真实类别数，导致现有方法因原型不足而无法全面学习概念。为解决此问题，我们提出一种自适应探测机制，引入可学习的潜在原型来扩展聚类原型（中心）。由于潜在原型缺乏真实标签，我们开发了一个自监督原型学习框架，以端到端方式优化潜在原型。其次，聚类计算成本高昂，而传统策略同时对标注和未标注实例进行聚类进一步加剧了这一问题。为提升效率，我们仅对未标注实例进行聚类，随后利用引入的潜在原型扩展聚类原型，以快速探索新类别。尽管所提方法简洁，但在广泛数据集上的大量实证分析表明，我们的方法持续取得最先进的结果。具体而言，在Stanford Cars数据集上，我们的方法以显著优势超越最接近的竞争对手，性能提升幅度达\textbf{9.7}$\%$；在Herbarium 19数据集中，聚类效率提升\textbf{12倍}。代码与检查点将在\url{https://github.com/xjtuYW/PNP.git}公开发布。