论文标题
基于保证金的几级课程学习，班级级别的缓解措施
Margin-Based Few-Shot Class-Incremental Learning with Class-Level Overfitting Mitigation
论文作者
论文摘要
很少有类别的课程学习（FSCIL）旨在逐步识别新的类别，只有很少的训练样本在基本类别的（预 - ）培训后，具有足够的样本，重点是基础级的表现和新颖的类概括。对基类培训的众所周知的修改是将余量限制在基层分类中。但是，存在一个困境，我们几乎无法通过在基础级训练期间应用边缘来同时实现良好的基础表现和新型级别的概括，这仍在探索中。在本文中，我们研究了FSCIL这种困境的原因。我们首先将这一难题解释为从模式学习方面的班级过度拟合（CO）问题，然后找到其原因在于基于学习保证金模式的易于满足的限制。基于分析，我们提出了一种基于保证金的新型FSCIL方法，以通过从基于保证金的模式本身提供额外的约束来减轻CO问题。对CIFAR100，CALTECH-USCD BIRDS-200-200-2011（CUB200）和MINIIMAGENET进行的广泛实验表明，所提出的方法有效地减轻了CO问题并实现了最新的性能。
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.
