Exploiting Fine-Grained Prototype Distribution for Boosting Unsupervised Class Incremental Learning

TL;DR

This paper introduces a novel approach for unsupervised class incremental learning that models class distributions with fine-grained prototypes and employs a granularity alignment technique to improve unknown class discovery and reduce forgetting.

Contribution

It proposes a new method combining prototype modeling and granularity alignment to enhance unsupervised class incremental learning performance.

Findings

Outperforms existing state-of-the-art methods on five datasets.

Effectively discovers unknown classes in an unsupervised setting.

Reduces catastrophic forgetting through overlap minimization.

Abstract

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.