logo
科言猫学术研究的AI总结
language
手机端手机端
  • Phone Feature微信小程序
简体中文简体中文
notice消息通知
博客博客
delete
arrow
返回

PAL: Prompting analytic learning with missing modality for multi-modal class-incremental learning

delete2026-03-14
delete0
PRE
AI
X
Xianghu Yue
Y
Yiming Chen
X
Xueyi Zhang
X
Xiaoxue Gao
M
Mengling Feng
M
Mingrui Lao *
庄辉平 封面图
庄辉平 (Huiping Zhuang) *
H
Haizhou Li
DOI：10.1016/j.patcog.2026.113467delete
delete原文链接
delete原文求助
delete分享
delete收藏
摘要

摘要

En 中文
• 我们提出了PAL——一种新颖的无示例技术，用于解决多模态CIL过程中缺失模态的问题。 • PAL无缝地将模态特定的提示整合到分析学习中，将缺失模态的MMCIL重新定义为RLS任务，并通过提示调优解决固有的欠拟合限制。 • 实验结果表明，PAL优于近期最先进的方法，展示了其在解决缺失模态问题上的鲁棒性，以及在进行CIL过程中保持高分类精度的能力。
Keyword:
PAL
missing modality
multi-modal CIL
prompt tuning
class-incremental learning

期刊

Pattern Recognition 封面图
Pattern Recognition
IF:
7.6
论文数:
1.3W
被引数:
4.5W

机构

T
The Chinese University of Hong Kong
学者数:
3.8K
论文数: 1.9K
被引数: 3
T
tianjin university
学者数:
8.0W
论文数: 5.8W
被引数: 88
N
national university of defense technology
学者数:
5.0K
论文数: 1.5K
被引数: 0
N
national university of singapore
学者数:
4.6K
论文数: 2.4K
被引数: 1
S
South China University of Technology
学者数:
2.3K
论文数: 853
被引数: 8.3W
A
a star
学者数:
107
论文数: 51
被引数: 0
学者 查看更多机构
引用论文

引用论文

Deep Audio-Visual Beamforming for Speaker Localization
errieee signal processing magazine
IF3.9
err2022-01-01
err9
PREAI
errQian, Xinyuan; Zhang, Qiquan; Guan, Guohui; Xue, Wei
err分享
err收藏
End-to-End Audiovisual Speech Recognition System With Multitask Learning具有多任务学习的端到端视听语音识别系统
errIEEE TRANSACTIONS ON MULTIMEDIA
IF9.7
err2021-01-01
err58
errOAAI
errTao, Fei; Busso, Carlos
err分享
err收藏
Memory Efficient Class-Incremental Learning for Image Classification用于图像分类的记忆高效类增量学习
errIEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
IF8.9
err2022-10-01
err50
errOAAI
errZhao, Hanbin; Wang, Hui; Fu, Yongjian; Wu, Fei; Li, Xi
err分享
err收藏
Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations视觉基因组: 使用众包密集图像注释连接语言和视觉
errINTERNATIONAL JOURNAL OF COMPUTER VISION
IF9.3
err2017-02-06
err3.1K
errOAAI
errKrishna, Ranjay; Zhu, Yuke; Groth, Oliver; Johnson, Justin; Hata, Kenji; Kravitz, Joshua; Chen, Stephanie; Kalantidis, Yannis; Li, Li-Jia; Shamma, David A.; Bernstein, Michael S.; Li Fei-Fei
err分享
err收藏
Deep Audio-Visual Speech Recognition
errIEEE Transactions on Pattern Analysis and Machine Intelligence
IF0
err2022-12-01
err0
errOAAI
errTriantafyllos Afouras; Joon Son Chung; Andrew Senior; Oriol Vinyals; Andrew Zisserman
err分享
err收藏
Blockwise Recursive Moore-Penrose Inverse for Network Learning
errieee transactions on cybernetics
IF8.7
err2022-05-01
err15
PREAI
errZhuang, Huiping; Lin, Zhiping; Toh, Kar-Ann
err分享
err收藏
Learning without Forgetting学习不遗忘
errIEEE Transactions on Pattern Analysis and Machine Intelligence
IF0
err2018-12-01
err0
errOAAI
errZhizhong Li; Derek Hoiem
err分享
err收藏
Image-Text Embedding Learning via Visual and Textual Semantic Reasoning
errIEEE Transactions on Pattern Analysis and Machine Intelligence
IF0
err2023-01-01
err0
PREAI
errKunpeng Li; Yulun Zhang; Kai Li; Yuanyuan Li; Yun Fu
err分享
err收藏
Class incremental learning with self-supervised pre-training and prototype learning具有自监督预训练和原型学习的类增量学习
errPATTERN RECOGNITION
IF7.6
err2025-01-01
err0
errOAAI
errLiu, Wenzhuo; Wu, Xin-Jian; Zhu, Fei; Yu, Ming-Ming; Wang, Chuang; Liu, Cheng-Lin
err分享
err收藏
Continual learning with high-order experience replay for dynamic network embedding
errPATTERN RECOGNITION
IF7.6
err2025-03-01
err0
PREAI
errWang, Zhizheng; Sun, Yuanyuan; Zhang, Xiaokun; Xu, Bo; Yang, Zhihao; Lin, Hongfei
err分享
err收藏
学者 查看更多内容