DIMoE-Adapters：动态专家进化用于视觉语言模型的持续学习
DIMoE-Adapters: Dynamic Expert Evolution for Continual Learning in Vision-Language Models
AI总结：
本文提出DIMoE-Adapters框架，通过动态专家进化方法平衡持续学习中的稳定性与可塑性，解决多领域任务增量学习中的领域迁移问题。
摘要：
持续学习使视觉语言模型能够在不重新训练的情况下积累知识并适应变化的任务。然而，在多领域任务增量学习中，大规模领域迁移加剧了稳定性与可塑性的矛盾。现有方法依赖固定架构和静态参数分配，限制了对新领域的适应并加剧灾难性遗忘。为了解决这些挑战，我们提出DIMoE-Adapters，一种动态增量混合专家适配框架，引入动态专家进化范式来平衡稳定性与可塑性。该范式通过两个协作组件：自校准专家进化（SCEE）和原型引导专家选择（PGES）实现。SCEE通过专家优化动态构建和进化稀疏专家池，提高可塑性并减少冗余容量。PGES根据SCEE构建的池控制专家利用，提高在之前遇到和未见任务上的稳定性。大量实验表明，DIMoE-Adapters在各种设置中均优于现有最先进方法。
英文摘要：
Continual learning enables vision-language models to accumulate knowledge and adapt to evolving tasks without retraining from scratch. However, in multi-domain task-incremental learning, large domain shifts intensify the stability-plasticity dilemma. Most existing methods rely on fixed architectures with statically allocated parameters, which limits adaptation to new domains and aggravates catastrophic forgetting. To address these challenges, we propose DIMoE-Adapters, a Dynamic Incremental Mixture-of-Experts Adapters framework that introduces a dynamic expert evolution paradigm to balance stability and plasticity. This paradigm is implemented through two collaborative components: Self-Calibrated Expert Evolution (SCEE) and Prototype-Guided Expert Selection (PGES). SCEE constructs and evolves a sparse expert pool through expert optimization dynamics, improving plasticity while reducing redundant capacity. PGES controls expert utilization based on the pool shaped by SCEE, improving stability across both previously encountered and unseen tasks. Extensive experiments show that DIMoE-Adapters outperforms previous state-of-the-art methods across various settings.
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。
