全局预固定，局部调整：一种简单而有效的持续学习对比策略
Global Pre-fixing, Local Adjusting: A Simple yet Effective Contrastive Strategy for Continual Learning
AI总结：
本文提出GPLASC对比策略，通过全局预固定等角紧框架划分任务区域、局部调整任务内特征结构，同时缓解任务间与任务内混淆，提升持续学习性能。
摘要：
持续学习（CL）涉及从不断演变的任务中获取和积累知识，同时缓解灾难性遗忘。近年来，利用对比损失来构建更具可迁移性且更不易遗忘的表示，已成为持续学习中一个有前景的方向。尽管取得了一定进展，但由于任务间特征和任务内特征产生的混淆，其性能仍然受限。为了解决这一问题，我们提出了一种简单而有效的对比策略，称为用于监督对比学习的全局预固定、局部调整（GPLASC）。具体而言，为了避免任务级混淆，我们将表示的整个单位超球面划分为互不重叠的区域，这些区域的中心构成一个任务间预固定的等角紧框架（ETF）。同时，对于各个任务，我们的方法有助于规范特征结构，并在各自分配的区域内部形成任务内可调整的ETF。因此，我们的方法同时确保了任务之间和任务内部具有判别性的特征结构，并且可以无缝集成到任何现有的对比持续学习框架中。大量实验验证了其有效性。
英文摘要：
Continual learning (CL) involves acquiring and accumulating knowledge from evolving tasks while alleviating catastrophic forgetting. Recently, leveraging contrastive loss to construct more transferable and less forgetful representations has been a promising direction in CL. Despite advancements, their performance is still limited due to confusion arising from both inter-task and intra-task features. To address the problem, we propose a simple yet effective contrastive strategy named \textbf{G}lobal \textbf{P}re-fixing, \textbf{L}ocal \textbf{A}djusting for \textbf{S}upervised \textbf{C}ontrastive learning (GPLASC). Specifically, to avoid task-level confusion, we divide the entire unit hypersphere of representations into non-overlapping regions, with the centers of the regions forming an inter-task pre-fixed \textbf{E}quiangular \textbf{T}ight \textbf{F}rame (ETF). Meanwhile, for individual tasks, our method helps regulate the feature structure and form intra-task adjustable ETFs within their respective allocated regions. As a result, our method \textit{simultaneously} ensures discriminative feature structures both between tasks and within tasks and can be seamlessly integrated into any existing contrastive continual learning framework. Extensive experiments validate its effectiveness.
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。
