数据采集与处理2025，Vol.40Issue(5)：1122-1138,17.DOI:10.16337/j.1004-9037.2025.05.002
多模态持续学习方法研究进展
Research Progress on Multimodal Continual Learning Methods
摘要
Abstract
Multimodal continual learning(MMCL),as a significant research direction in the fields of machine learning and artificial intelligence,aims to achieve continuous knowledge accumulation and task adaptation through the integration of multiple modal data(such as images,text,audio,etc.).Compared with traditional single-modal learning methods,MMCL not only enables parallel processing of multi-source heterogeneous data,but also effectively retains existing knowledge while adapting to new task requirements,demonstrating immense application potential in intelligent systems.This paper provides a systematic review of multimodal continual learning.Firstly,the fundamental theoretical framework of MMCL is elaborated from three dimensions:Basic concepts,evaluation systems,and classical single-modal continual learning methods.Secondly,the advantages and challenges of MMCL in practical applications are thoroughly analyzed:Despite its significant advantages in multimodal information fusion,it still faces critical challenges such as modal imbalance and heterogeneous fusion,which not only constrain the performance of current methods but also indicate future research directions.Based on this,the paper then comprehensively reviews the research status and latest advancements in MMCL methods from four main aspects:Replay-based,regularization-based,parameter isolation-based,and large model-based approaches.Finally,a forward-looking perspective on the future development trends of MMCL is presented.关键词
多模态持续学习/模态对齐/灾难性遗忘/预训练模型/任务适应性Key words
multimodal continual learning(MMCL)/modality alignment/catastrophic forgetting/pre-trained models/task adaptation分类
信息技术与安全科学引用本文复制引用
张伟,钱龙玥,张林,李腾..多模态持续学习方法研究进展[J].数据采集与处理,2025,40(5):1122-1138,17.基金项目
新一代人工智能国家科技重大专项(2021ZD0112002). （2021ZD0112002）
