Although data-free incremental learning methods are memory-friendly, accurately estimating and counteracting representation shifts is challenging in the absence of historical data. This paper addresses this thorny problem by proposing a novel incremental learning method inspired by human analogy capabilities. Specifically, we design an analogy-making mechanism to remap the new data into the old class by prompt tuning. It mimics the feature distribution of the target old class on the old model using only samples of new classes. The learnt prompts are further used to estimate and counteract the representation shift caused by fine-tuning for the historical prototypes. The proposed method sets up new state-of-the-art performance on four incremental learning benchmarks under both the class and domain incremental learning settings. It consistently outperforms data-replay methods by only saving feature prototypes for each class. It has almost hit the empirical upper bound by joint training on the Core50 benchmark. The code will be released at \url{https://github.com/ZhihengCV/A-Prompts}.

翻译：尽管无数据增量学习方法内存友好，但在缺乏历史数据的情况下，准确估计并抵消表示偏移极具挑战性。本文受人类类比能力启发，提出一种新颖的增量学习方法以解决这一棘手问题。具体而言，我们设计了一种类比生成机制，通过提示调优将新数据重新映射至旧类别。该方法仅利用新类别样本，在旧模型上模拟目标旧类别的特征分布。进一步地，学习得到的提示被用于估计并抵消因微调历史原型而产生的表示偏移。所提方法在四个增量学习基准测试中，于类别增量学习与领域增量学习两种场景下均实现了最新最优性能。通过仅保存每个类别的特征原型，该方法持续优于数据重放型方法，并在Core50基准测试上几乎达到联合训练的经验上界。相关代码将在\url{https://github.com/ZhihengCV/A-Prompts}发布。