Class-incremental learning (CIL) is a particularly challenging variant of continual learning, where the goal is to learn to discriminate between all classes presented in an incremental fashion. Existing approaches often suffer from excessive forgetting and imbalance of the scores assigned to classes that have not been seen together during training. In this study, we introduce a novel approach, Prediction Error-based Classification (PEC), which differs from traditional discriminative and generative classification paradigms. PEC computes a class score by measuring the prediction error of a model trained to replicate the outputs of a frozen random neural network on data from that class. The method can be interpreted as approximating a classification rule based on Gaussian Process posterior variance. PEC offers several practical advantages, including sample efficiency, ease of tuning, and effectiveness even when data are presented one class at a time. Our empirical results show that PEC performs strongly in single-pass-through-data CIL, outperforming other rehearsal-free baselines in all cases and rehearsal-based methods with moderate replay buffer size in most cases across multiple benchmarks.

翻译：类别增量学习（Class-incremental learning, CIL）是持续学习中极具挑战性的变体，其目标是增量式学习区分所有已出现的类别。现有方法常面临严重的遗忘问题，且对训练中未曾同时出现的类别存在评分失衡。本研究提出一种新方法——基于预测误差的分类（Prediction Error-based Classification, PEC），该方法区别于传统的判别式与生成式分类范式。PEC通过测量模型在某一类数据上复制冻结随机神经网络输出的预测误差来计算类别得分。该方法可被解释为基于高斯过程后验方差的分类规则近似。PEC具有多种实际优势，包括样本效率、易于调参，甚至在数据逐类呈现时仍能保持有效性。实验结果表明，在单次遍历数据的CIL场景中，PEC在所有无记忆回放基线方法中均表现优异，且在多数基准测试中，当采用中等回放缓冲区大小时，其性能超越基于记忆回放的方法。