The dynamic nature of open-world scenarios has attracted more attention to class incremental learning (CIL). However, existing CIL methods typically presume the availability of complete ground-truth labels throughout the training process, an assumption rarely met in practical applications. Consequently, this paper explores a more challenging problem of unsupervised class incremental learning (UCIL). The essence of addressing this problem lies in effectively capturing comprehensive feature representations and discovering unknown novel classes. To achieve this, we first model the knowledge of class distribution by exploiting fine-grained prototypes. Subsequently, a granularity alignment technique is introduced to enhance the unsupervised class discovery. Additionally, we proposed a strategy to minimize overlap between novel and existing classes, thereby preserving historical knowledge and mitigating the phenomenon of catastrophic forgetting. Extensive experiments on the five datasets demonstrate that our approach significantly outperforms current state-of-the-art methods, indicating the effectiveness of the proposed method.

翻译：开放世界场景的动态特性使得类增量学习（CIL）受到越来越多的关注。然而，现有的CIL方法通常假设在整个训练过程中能够获得完整的真实标签，这一假设在实际应用中很少得到满足。因此，本文探讨了一个更具挑战性的问题——无监督类增量学习（UCIL）。解决该问题的关键在于有效捕获全面的特征表示并发现未知的新类别。为此，我们首先通过利用细粒度原型对类别分布知识进行建模。随后，引入粒度对齐技术以增强无监督的类别发现能力。此外，我们提出了一种策略来最小化新类别与已有类别之间的重叠，从而保留历史知识并缓解灾难性遗忘现象。在五个数据集上进行的大量实验表明，我们的方法显著优于当前最先进的方法，验证了所提方法的有效性。