Exemplar-free class-incremental learning (EFCIL) aims to mitigate catastrophic forgetting in class-incremental learning without available historical data. Compared with its counterpart (replay-based CIL) that stores historical samples, the EFCIL suffers more from forgetting issues under the exemplar-free constraint. In this paper, inspired by the recently developed analytic learning (AL) based CIL, we propose a representation enhanced analytic learning (REAL) for EFCIL. The REAL constructs a dual-stream base pretraining (DS-BPT) and a representation enhancing distillation (RED) process to enhance the representation of the extractor. The DS-BPT pretrains model in streams of both supervised learning and self-supervised contrastive learning (SSCL) for base knowledge extraction. The RED process distills the supervised knowledge to the SSCL pretrained backbone and facilitates a subsequent AL-basd CIL that converts the CIL to a recursive least-square problem. Our method addresses the issue of insufficient discriminability in representations of unseen data caused by a frozen backbone in the existing AL-based CIL. Empirical results on various datasets including CIFAR-100, ImageNet-100 and ImageNet-1k, demonstrate that our REAL outperforms the state-of-the-arts in EFCIL, and achieves comparable or even more superior performance compared with the replay-based methods.

翻译：无示例类增量学习（EFCIL）旨在无历史数据可用时缓解类增量学习中的灾难性遗忘问题。与存储历史样本的基于回放的类增量学习方法相比，EFCIL在无示例约束下更容易遭受遗忘问题。受近期发展的基于解析学习（AL）的类增量学习方法启发，本文提出了一种面向EFCIL的表示增强解析学习（REAL）方法。REAL构建了双流基础预训练（DS-BPT）和表示增强蒸馏（RED）过程，以增强特征提取器的表示能力。DS-BPT通过监督学习与自监督对比学习（SSCL）双流预训练模型，用于提取基础知识。RED过程将监督知识蒸馏至SSCL预训练骨干网络，并促进后续基于AL的类增量学习——该过程将类增量学习转化为递归最小二乘问题。本方法解决了现有基于AL的类增量学习中因冻结骨干网络导致的未见数据表示判别性不足问题。在CIFAR-100、ImageNet-100和ImageNet-1k等多个数据集上的实验结果表明，我们的REAL方法在EFCIL任务中达到了最先进水平，并且与基于回放的方法相比，取得了相当甚至更优的性能表现。