The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been devoted to incorporating the benefits of pre-training. However, how to adaptively exploit the pre-trained knowledge for each incremental task while maintaining its generalizability remains an open question. In this work, we present an extensive analysis for continual learning on a pre-trained model (CLPM), and attribute the key challenge to a progressive overfitting problem. Observing that selectively reducing the learning rate can almost resolve this issue in the representation layer, we propose a simple but extremely effective approach named Slow Learner with Classifier Alignment (SLCA), which further improves the classification layer by modeling the class-wise distributions and aligning the classification layers in a post-hoc fashion. Across a variety of scenarios, our proposal provides substantial improvements for CLPM (e.g., up to 49.76%, 50.05%, 44.69% and 40.16% on Split CIFAR-100, Split ImageNet-R, Split CUB-200 and Split Cars-196, respectively), and thus outperforms state-of-the-art approaches by a large margin. Based on such a strong baseline, critical factors and promising directions are analyzed in-depth to facilitate subsequent research.

翻译：持续学习的目标是提升识别模型在学习顺序到达数据时的性能。尽管现有工作大多建立在从零开始学习的预设上，但越来越多的研究致力于引入预训练优势。然而，如何在利用预训练知识适应每个增量任务的同时保持其泛化性仍是一个开放性问题。本文对基于预训练模型的持续学习（CLPM）进行了深入分析，将关键挑战归因于渐进式过拟合问题。通过观察发现，在表示层中选择性降低学习率几乎可以解决该问题，我们提出了一种简单但极其有效的方法——慢学习器与分类器对齐（SLCA），该方法通过建模类别分布并以事后方式对齐分类层，进一步改进了分类层。在多种场景下，我们的方法显著提升了CLPM性能（例如，在Split CIFAR-100、Split ImageNet-R、Split CUB-200和Split Cars-196上分别提升高达49.76%、50.05%、44.69%和40.16%），从而大幅超越现有最佳方法。基于该强力基线，我们深入分析了关键因素与有前景的研究方向，以促进后续研究。