Recent Advances of Multimodal Continual Learning: A Comprehensive Survey

计算机科学 数据科学
作者
Dianzhi Yu,Xinni Zhang,Yankai Chen,Aiwei Liu,Yifei Zhang,Philip S. Yu,Irwin King
出处
期刊:Cornell University - arXiv
标识
DOI:10.48550/arxiv.2410.05352
摘要

Continual learning (CL) aims to empower machine learning models to learn continually from new data, while building upon previously acquired knowledge without forgetting. As machine learning models have evolved from small to large pre-trained architectures, and from supporting unimodal to multimodal data, multimodal continual learning (MMCL) methods have recently emerged. The primary challenge of MMCL is that it goes beyond a simple stacking of unimodal CL methods, as such straightforward approaches often yield unsatisfactory performance. In this work, we present the first comprehensive survey on MMCL. We provide essential background knowledge and MMCL settings, as well as a structured taxonomy of MMCL methods. We categorize existing MMCL methods into four categories, i.e., regularization-based, architecture-based, replay-based, and prompt-based methods, explaining their methodologies and highlighting their key innovations. Additionally, to prompt further research in this field, we summarize open MMCL datasets and benchmarks, and discuss several promising future directions for investigation and development. We have also created a GitHub repository for indexing relevant MMCL papers and open resources available at https://github.com/LucyDYu/Awesome-Multimodal-Continual-Learning.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
浪里小白龙完成签到,获得积分10
2秒前
薛强完成签到,获得积分10
2秒前
Orange应助晚灯君采纳,获得10
3秒前
daisy完成签到,获得积分10
3秒前
5秒前
5秒前
纯情的碧玉完成签到,获得积分10
5秒前
panppppa发布了新的文献求助10
5秒前
爆米花应助auggy采纳,获得10
6秒前
虞丹萱发布了新的文献求助10
6秒前
情怀应助健壮的紫菱采纳,获得30
6秒前
8秒前
8秒前
领导范儿应助ll采纳,获得10
9秒前
sfsfes应助AW采纳,获得10
9秒前
蓉城发布了新的文献求助150
9秒前
彭于晏应助noobmaster采纳,获得10
9秒前
luanzh发布了新的文献求助10
11秒前
11秒前
所所应助12344采纳,获得10
11秒前
白夜完成签到,获得积分10
11秒前
14秒前
嗯哼完成签到,获得积分20
14秒前
核桃应助科研通管家采纳,获得10
14秒前
CodeCraft应助科研通管家采纳,获得10
15秒前
15秒前
科研通AI5应助科研通管家采纳,获得10
15秒前
敬老院1号应助科研通管家采纳,获得200
15秒前
15秒前
Xiaoxiao应助科研通管家采纳,获得10
15秒前
15秒前
隐形曼青应助科研通管家采纳,获得10
15秒前
15秒前
ll完成签到,获得积分20
15秒前
15秒前
嗯哼发布了新的文献求助30
16秒前
SciGPT应助感动水杯采纳,获得10
17秒前
17秒前
FashionBoy应助电闪采纳,获得10
17秒前
打卡下班应助chen采纳,获得10
17秒前
高分求助中
(禁止应助)【重要!!请各位详细阅读】【科研通的精品贴汇总】 10000
Semantics for Latin: An Introduction 1099
Robot-supported joining of reinforcement textiles with one-sided sewing heads 780
水稻光合CO2浓缩机制的创建及其作用研究 500
Logical form: From GB to Minimalism 500
2025-2030年中国消毒剂行业市场分析及发展前景预测报告 500
镇江南郊八公洞林区鸟类生态位研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 4158598
求助须知:如何正确求助?哪些是违规求助? 3694481
关于积分的说明 11666176
捐赠科研通 3386616
什么是DOI,文献DOI怎么找? 1857188
邀请新用户注册赠送积分活动 918236
科研通“疑难数据库(出版商)”最低求助积分说明 831434