Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting. Top-performing methods usually require a rehearsal buffer to store past pristine examples for experience replay, which, however, limits their practical value due to privacy and memory constraints. In this work, we present a simple yet effective framework, DualPrompt, which learns a tiny set of parameters, called prompts, to properly instruct a pre-trained model to learn tasks arriving sequentially without buffering past examples. DualPrompt presents a novel approach to attach complementary prompts to the pre-trained backbone, and then formulates the objective as learning task-invariant and task-specific "instructions". With extensive experimental validation, DualPrompt consistently sets state-of-the-art performance under the challenging class-incremental setting. In particular, DualPrompt outperforms recent advanced continual learning methods with relatively large buffer sizes. We also introduce a more challenging benchmark, Split ImageNet-R, to help generalize rehearsal-free continual learning research. Source code is available at https://github.com/google-research/l2p.
翻译:持续学习的目的是让单一模式能够学习一系列任务,而不会造成灾难性的遗忘。 顶级工作方法通常需要一个预演缓冲, 以存储以往的原始经验重现范例, 但是由于隐私和记忆限制,这些范例限制了它们的实际价值。 在这项工作中, 我们提出了一个简单而有效的框架, 即“ DualPrompt ”, 它学习了一套微小的参数, 称为“ 提示”, 以适当指导一个预培训模式, 来学习在不缓冲过去的例子的情况下按顺序完成的任务。 双级工作展示了一种新颖的方法, 将互补的提示点附加在培训前的骨干上, 然后将目标设计为学习任务和任务特定的“ 指令 ” 。 在广泛的实验性验证下, DualPrmpt 持续设定了在具有挑战性的等级环境下的最新艺术表现。 特别是, 双级方案超越了最近先进的持续学习方法, 缓冲大小。 我们还引入了一个更具挑战性的基准, SpletimageNet-R, 以帮助普及免费的连续学习研究。 源代码可在 https://github.com/goglegleglegleglegleglegle- reear2 上查阅。