面向可扩展类别增量学习的基于质心原型映射的适配器合并方法
Adapter Merging with Centroid Prototype Mapping for Scalable Class-Incremental Learning
AI总结：
该研究提出无样本存储的类别增量学习框架ACMap，通过适配器合并构建共享子空间结合质心原型映射，搭配早停策略提升可扩展性，实现恒定推理时间且准确率达当前最优水平。
摘要：
我们提出了ACMap（基于质心原型映射的适配器合并，Adapter Merging with Centroid Prototype Mapping），这是一种无样本存储的类别增量学习（CIL，class-incremental learning）框架，可同时解决灾难性遗忘和可扩展性问题。现有方法需在推理时间和准确率之间权衡，而ACMap将任务特定适配器整合为单个适配器，从而在不损失准确率的前提下实现跨任务的恒定推理时间。该框架采用适配器合并构建共享子空间，对齐任务表征并缓解遗忘；同时质心原型映射通过在共享子空间内持续适配表征来保持高准确率。为进一步提升可扩展性，我们引入早停策略，在任务数量增加时限制适配器合并操作。在五个基准数据集上的大量实验表明，ACMap的准确率与当前最优水平相当，同时推理时间可与现有最快方法媲美。代码可在https://github.com/tf63/ACMap获取。
英文摘要：
We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and scalability. While existing methods involve a trade-off between inference time and accuracy, ACMap consolidates task-specific adapters into a single adapter, thus achieving constant inference time across tasks without sacrificing accuracy. The framework employs adapter merging to build a shared subspace that aligns task representations and mitigates forgetting, while centroid prototype mapping maintains high accuracy by consistently adapting representations within the shared subspace. To further improve scalability, an early stopping strategy limits adapter merging as tasks increase. Extensive experiments on five benchmark datasets demonstrate that ACMap matches state-of-the-art accuracy while maintaining inference time comparable to the fastest existing methods. The code is available at https://github.com/tf63/ACMap.
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。
