层次双子空间解耦用于视觉-语言模型中的持续学习
Hierarchical Dual-Subspace Decoupling for Continual Learning in Vision-Language Models
AI总结：
本文提出HDSD框架，通过分解参数空间和结构化参数分解，减少子空间干扰和参数漂移，提升视觉-语言模型持续学习性能。
摘要：
本文提出HDSD框架，通过分解参数空间和结构化参数分解，减少子空间干扰和参数漂移，提升视觉-语言模型持续学习性能。
英文摘要：
Class-incremental learning aims to continuously acquire new knowledge while preserving previously learned information, thereby mitigating catastrophic forgetting. Existing methods primarily restrict parameter updates but often overlook their structural properties in high-dimensional spaces. From a subspace perspective, updates induced by different tasks tend to lie in multiple overlapping low-rank subspaces, leading to cross-task subspace interference and severe forgetting. To address this issue, we propose HDSD, a Hierarchical Dual-Subspace Decoupling framework for continual learning in vision-language models. Specifically, we introduce a lightweight Feature Modulation Module (FMM) that explicitly decomposes the parameter space into general and task-specific subspaces. Building on this design, we develop two complementary components. First, a General Fusion Module (GFM) evaluates relative parameter changes across tasks and uses an adaptive threshold to capture stable and transferable knowledge. Second, a Hierarchical Learning Module (HLM) performs structured parameter decomposition via Singular Value Decomposition (SVD) and uses a scaling mechanism to constrain updates within distinct subspace scales. Together, these designs reduce subspace interference and parameter drift. Extensive experiments on conventional benchmarks show that HDSD achieves state-of-the-art results.
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。
