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）由于禁止复用先前任务的数据而面临诸多挑战，因此容易遭受灾难性遗忘。近期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受到广泛关注。本文针对CIL探索了原型网络方法——该方法利用冻结的特征提取器生成新类原型，并基于特征与原型间的欧氏距离进行分类。通过分析类的特征分布，我们证明基于欧氏度量的分类方法对联合训练的特征有效。然而，在非平稳数据学习过程中，我们发现欧氏度量并非最优，且特征分布呈现异质性。为解决这一挑战，我们重新审视了各向异性马氏距离在CIL中的应用。此外，我们通过实证表明，建模特征协方差关系优于此前从正态分布采样特征并训练线性分类器的尝试。与现有方法不同，本方法可泛化至多样本与少样本CIL场景，以及域增量场景。值得注意的是，在不更新主干网络的情况下，我们的方法在多个标准持续学习基准上取得了最先进的结果。代码已开源：https://github.com/dipamgoswami/FeCAM。