用提示词和适配器实现轻量持续学习，缓解遗忘问题。
Adapter-Enhanced Semantic Prompting for Continual Learning
- 结合提示词与适配器，动态生成任务相关特征。
- 在三个数据集上表现优于现有方法，有效减少遗忘。
- 适合资源受限场景下的持续学习应用。
持续学习（CL）使模型能够适应不断变化的数据流。其主要挑战是灾难性遗忘，即新知识会覆盖旧知识。传统方法通常需要存储历史数据进行回放或在模型中添加额外分支来学习新知识，导致内存开销大。本文提出一种新型轻量级持续学习框架——适配器增强语义提示（AESP），融合提示调优与适配器技术。我们设计了语义引导的提示词以增强视觉特征的泛化能力，并利用适配器高效融合语义信息，旨在为持续学习任务学习更自适应的特征表示。此外，为选择合适的任务提示以实现特征适配，我们提出了一种新颖的提示匹配机制。在三个持续学习数据集上的大量实验表明，该方法在多个指标上均取得良好性能，展现出推进持续学习的潜力。
原文摘要 · Abstract (English)
Continual learning (CL) enables models to adapt to evolving data streams. A major challenge of CL is catastrophic forgetting, where new knowledge will overwrite previously acquired knowledge. Traditional methods usually retain the past data for replay or add additional branches in the model to learn new knowledge, which has high memory requirements. In this paper, we propose a novel lightweight CL framework, Adapter-Enhanced Semantic Prompting (AESP), which integrates prompt tuning and adapter techniques. Specifically, we design semantic-guided prompts to enhance the generalization ability of visual features and utilize adapters to efficiently fuse the semantic information, aiming to learn more adaptive features for the continual learning task. Furthermore, to choose the right task prompt for feature adaptation, we have developed a novel matching mechanism for prompt selection. Extensive experiments on three CL datasets demonstrate that our approach achieves favorable performance across multiple metrics, showing its potential for advancing CL.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。