Continual learning refers to the problem where the training data is available in sequential chunks, termed "tasks". The majority of progress in continual learning has been stunted by the problem of catastrophic forgetting, which is caused by sequential training of the model on streams of data. Moreover, it becomes computationally expensive to sequentially train large models multiple times. To mitigate both of these problems at once, we propose a novel method to continually train transformer-based vision models using low-rank adaptation and task arithmetic. Our method completely bypasses the problem of catastrophic forgetting, as well as reducing the computational requirement for training models on each task. When aided with a small memory of 10 samples per class, our method achieves performance close to full-set finetuning. We present rigorous ablations to support the prowess of our method.

我们提出了一种新颖的方法，利用低秩适应和任务算术，不断训练基于Transformer的视觉模型，绕过灾难性遗忘问题并减少训练计算需求。在每个类别仅使用10个样本的小内存的帮助下，我们的方法实现了接近于完整微调的性能，并通过严格的消融实验证明了我们方法的优势。

基于 LoRA 的持续学习的任务算术