Multi-Granularity Regularized Re-Balancing for Class Incremental Learning

TL;DR

This paper introduces MGRB, a novel assumption-agnostic method for class incremental learning that uses multi-granularity regularization to improve knowledge retention and class relation understanding amidst data imbalance.

Contribution

The paper proposes MGRB, a new approach combining re-balancing with class relation modeling via hierarchy-based regularization, addressing data imbalance without relying on specific bias assumptions.

Findings

MGRB outperforms existing methods on public datasets.

The method effectively mitigates catastrophic forgetting.

It enhances learning of both old and new classes.

Abstract

Deep learning models suffer from catastrophic forgetting when learning new tasks incrementally. Incremental learning has been proposed to retain the knowledge of old classes while learning to identify new classes. A typical approach is to use a few exemplars to avoid forgetting old knowledge. In such a scenario, data imbalance between old and new classes is a key issue that leads to performance degradation of the model. Several strategies have been designed to rectify the bias towards the new classes due to data imbalance. However, they heavily rely on the assumptions of the bias relation between old and new classes. Therefore, they are not suitable for complex real-world applications. In this study, we propose an assumption-agnostic method, Multi-Granularity Regularized re-Balancing (MGRB), to address this problem. Re-balancing methods are used to alleviate the influence of data imbalance; however, we empirically discover that they would under-fit new classes. To this end, we further design a novel multi-granularity regularization term that enables the model to consider the correlations of classes in addition to re-balancing the data. A class hierarchy is first constructed by grouping the semantically or visually similar classes. The multi-granularity regularization then transforms the one-hot label vector into a continuous label distribution, which reflects the relations between the target class and other classes based on the constructed class hierarchy. Thus, the model can learn the inter-class relational information, which helps enhance the learning of both old and new classes. Experimental results on both public datasets and a real-world fault diagnosis dataset verify the effectiveness of the proposed method.