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.

翻译：在持续学习背景下，原型——作为代表性的类别嵌入——在节省内存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，我们提出对比原型提示（CPP）方法。通过基于对比学习目标的任务特定提示调优，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测试上的评估表明，CPP相比最先进方法实现了4%至6%的显著提升。重要的是，CPP无需重放缓冲区，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的持续学习系统提供了一种创新方案。