Exemplar-free class-incremental learning (CIL) poses several challenges since it prohibits the rehearsal of data from previous tasks and thus suffers from catastrophic forgetting. Recent approaches to incrementally learning the classifier by freezing the feature extractor after the first task have gained much attention. In this paper, we explore prototypical networks for CIL, which generate new class prototypes using the frozen feature extractor and classify the features based on the Euclidean distance to the prototypes. In an analysis of the feature distributions of classes, we show that classification based on Euclidean metrics is successful for jointly trained features. However, when learning from non-stationary data, we observe that the Euclidean metric is suboptimal and that feature distributions are heterogeneous. To address this challenge, we revisit the anisotropic Mahalanobis distance for CIL. In addition, we empirically show that modeling the feature covariance relations is better than previous attempts at sampling features from normal distributions and training a linear classifier. Unlike existing methods, our approach generalizes to both many- and few-shot CIL settings, as well as to domain-incremental settings. Interestingly, without updating the backbone network, our method obtains state-of-the-art results on several standard continual learning benchmarks. Code is available at https://github.com/dipamgoswami/FeCAM.

翻译：无范例类增量学习（CIL）因禁止重复使用先前任务的数据而面临诸多挑战，尤其容易遭受灾难性遗忘。近年来，通过冻结首个任务后的特征提取器来增量学习分类器的方法备受关注。本文探究了面向CIL的原型网络方法——该方法利用冻结的特征提取器生成新类别原型，并根据特征与原型的欧氏距离进行分类。通过对类别特征分布的分析，我们发现基于欧氏度量的分类方法在联合训练的特征上表现良好。然而，当处理非平稳数据时，欧氏度量并非最优选择，且特征分布呈现异质性。为应对这一挑战，我们重新审视了各向异性马氏距离在CIL中的应用。此外，实验表明，对特征协方差关系进行建模优于此前从正态分布中采样特征并训练线性分类器的尝试。与现有方法不同，本方法不仅适用于多样本和小样本CIL场景，还可扩展至领域增量场景。值得注意的是，在不更新主干网络的情况下，我们在多个标准持续学习基准上取得了最先进的结果。代码开源地址：https://github.com/dipamgoswami/FeCAM。