Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learning
This addresses a more practical version of class incremental learning for open-world scenarios where complete labels are unavailable, representing a meaningful but incremental advance.
The paper tackles unsupervised class incremental learning (UCIL) by modeling class distribution with fine-grained prototypes and introducing granularity alignment to enhance class discovery, achieving significant performance improvements over state-of-the-art methods across five datasets.
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.