用提示微调引导原型以实现无重放持续学习
Steering Prototypes with Prompt-tuning for Rehearsal-free Continual Learning
AI总结：
本文提出对比原型提示（CPP）方法，通过任务特定提示微调和对比学习解决持续学习中的语义漂移与原型干扰，在四个类增量基准上超越现有方法4%至6%，且无需重放缓冲区。
摘要：
在持续学习背景下，原型——作为代表性类别嵌入——在内存节省和缓解灾难性遗忘方面具有优势。然而，与语义漂移和原型干扰相关的挑战仍然存在。在本研究中，我们引入了对比原型提示（CPP）方法。通过基于对比学习目标的任务特定提示微调，我们有效解决了上述两个挑战。我们在四个具有挑战性的类增量基准上的评估表明，CPP相较于最先进的方法实现了4%至6%的显著提升。重要的是，CPP无需重放缓冲区运行，并缩小了持续学习与离线联合学习之间的性能差距，为基于Transformer的持续学习系统提出了一种创新方案。
英文摘要：
In the context of continual learning, prototypes-as representative class embeddings-offer advantages in memory conservation and the mitigation of catastrophic forgetting. However, challenges related to semantic drift and prototype interference persist. In this study, we introduce the Contrastive Prototypical Prompt (CPP) approach. Through task-specific prompt-tuning, underpinned by a contrastive learning objective, we effectively address both aforementioned challenges. Our evaluations on four challenging class-incremental benchmarks reveal that CPP achieves a significant 4% to 6% improvement over state-of-the-art methods. Importantly, CPP operates without a rehearsal buffer and narrows the performance divergence between continual and offline joint-learning, suggesting an innovative scheme for Transformer-based continual learning systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
