Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation

Yixiong Zou, Shanghang Zhang, Yuhua Li, Ruixuan Li

Keywords: Few-shot class-incremental learning, Class-level overfitting, Margin-based classification

Abstract: Few-shot class-incremental learning (FSCIL) is designed to incrementally recognize novel classes with only few training samples after the (pre-)training on base classes with sufficient samples, which focuses on both base-class performance and novel-class generalization. A well known modification to the base-class training is to apply a margin to the base-class classification. However, a dilemma exists that we can hardly achieve both good base-class performance and novel-class generalization simultaneously by applying the margin during the base-class training, which is still under explored. In this paper, we study the cause of such dilemma for FSCIL. We first interpret this dilemma as a class-level overfitting (CO) problem from the aspect of pattern learning, and then find its cause lies in the easily-satisfied constraint of learning margin-based patterns. Based on the analysis, we propose a novel margin-based FSCIL method to mitigate the CO problem by providing the pattern learning process with extra constraint from the margin-based patterns themselves. Extensive experiments on CIFAR100, Caltech-USCD Birds-200-2011 (CUB200), and miniImageNet demonstrate that the proposed method effectively mitigates the CO problem and achieves state-of-the-art performance.

TL;DR: To mitigate class-level overfitting (CO) in margin-based classification for the few-shot class-incremental learning task, we first interpret CO from pattern learning, and then propose a method to mitigate CO and achieve SOTA performance.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/arxiv:2210.04524/code)