Self-Paced Imbalance Rectification for Class Incremental Learning

TL;DR

This paper introduces a self-paced imbalance rectification method for class incremental learning that dynamically balances old and new class representations, improving stability and performance in incremental tasks.

Contribution

It proposes a novel scheme combining frequency compensation, inheritance transfer, and attenuation mechanisms to enhance class imbalance handling in incremental learning.

Findings

Outperforms state-of-the-art methods on three benchmarks.

Achieves stable incremental learning performance.

Effectively mitigates old class repetition and confusion.

Abstract

Exemplar-based class-incremental learning is to recognize new classes while not forgetting old ones, whose samples can only be saved in limited memory. The ratio fluctuation of new samples to old exemplars, which is caused by the variation of memory capacity at different environments, will bring challenges to stabilize the incremental optimization process. To address this problem, we propose a novel self-paced imbalance rectification scheme, which dynamically maintains the incremental balance during the representation learning phase. Specifically, our proposed scheme consists of a frequency compensation strategy that adjusts the logits margin between old and new classes with the corresponding number ratio to strengthen the expression ability of the old classes, and an inheritance transfer strategy to reduce the representation confusion by estimating the similarity of different classes in the old embedding space. Furthermore, a chronological attenuation mechanism is proposed to mitigate the repetitive optimization of the older classes at multiple step-wise increments. Extensive experiments on three benchmarks demonstrate stable incremental performance, significantly outperforming the state-of-the-art methods.