Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation
This addresses a specific bottleneck in incremental learning for AI systems needing to adapt to new classes with limited data, though it is incremental as it builds on existing margin-based approaches.
The paper tackles the dilemma in few-shot class-incremental learning where applying a margin during base-class training harms novel-class generalization, identifying it as a class-level overfitting problem and proposing a method to mitigate it. The method achieves state-of-the-art performance on datasets like CIFAR100, CUB200, and miniImageNet.
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.