Are Mixture-of-Modality-Experts Transformers Robust to Missing Modality During Training and Inferring?

模态(人机交互) 人工智能 变压器 计算机科学 心理学 工程类 电气工程 电压
作者
Yan Gao,Tong Xu,Enhong Chen
出处
期刊:IFIP advances in information and communication technology 卷期号:: 157-172
标识
DOI:10.1007/978-3-031-57808-3_12
摘要

It is commonly seen that the imperfect multi-modal data with missing modality appears in realistic application scenarios, which usually break the data completeness assumption of multi-modal analysis. Therefore, large efforts in multi-modal learning communities have been made on the robust solution for modality-missing data. Recently, pre-trained models based on Mixture-of-Modality-Experts (MoME) Transformers have been proposed, which achieved competitive performance in various downstream tasks, by utilizing different experts of feed-forward networks for single/multi modal inputs. One natural question arises: are Mixture-of-Modality-Experts Transformers robust to missing modality? To that end, in this paper, we conduct a deep investigation on MoME Transformer under the missing modality problem. Specifically, we propose a novel multi-task learning strategy, which leverages a uniform model to handle missing modalities during training and inference. In this way, the MoME Transformer will be empowered with robustness to missing modality. To validate the effectiveness of our proposed method, we conduct extensive experiments on three popular datasets, which indicate our method could outperform the state-of-the-art (SOTA) methods with a large margin.
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
搜集达人应助杜兰特工队采纳,获得10
5秒前
热心市民小红花应助牛马采纳,获得10
7秒前
热心市民小红花应助牛马采纳,获得10
7秒前
7秒前
Ava应助WJM采纳,获得10
11秒前
科研通AI2S应助nczpf2010采纳,获得10
12秒前
酷酷飞烟发布了新的文献求助10
12秒前
Bressanone发布了新的文献求助10
14秒前
李健的小迷弟应助老吴采纳,获得10
14秒前
大气的雅山完成签到,获得积分10
16秒前
shaoshao86完成签到,获得积分10
22秒前
22秒前
华仔应助科研通管家采纳,获得10
22秒前
逆时针应助科研通管家采纳,获得10
22秒前
MchemG应助科研通管家采纳,获得10
22秒前
研友_VZG7GZ应助科研通管家采纳,获得10
22秒前
wang应助科研通管家采纳,获得10
22秒前
wang应助科研通管家采纳,获得10
22秒前
ding应助科研通管家采纳,获得10
22秒前
上官若男应助科研通管家采纳,获得10
23秒前
思源应助科研通管家采纳,获得10
23秒前
田様应助科研通管家采纳,获得10
23秒前
小北发布了新的文献求助10
23秒前
NexusExplorer应助Quinna采纳,获得10
25秒前
26秒前
26秒前
量子星尘发布了新的文献求助10
28秒前
WJM发布了新的文献求助10
32秒前
老吴发布了新的文献求助10
33秒前
34秒前
佳语妍说完成签到,获得积分10
35秒前
36秒前
37秒前
酷波er应助平淡的凝竹采纳,获得10
38秒前
40秒前
小星星发布了新的文献求助10
40秒前
田様应助c_123采纳,获得10
40秒前
43秒前
43秒前
无所归兮应助微7采纳,获得30
43秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3989069
求助须知:如何正确求助?哪些是违规求助? 3531351
关于积分的说明 11253589
捐赠科研通 3269939
什么是DOI,文献DOI怎么找? 1804851
邀请新用户注册赠送积分活动 882074
科研通“疑难数据库(出版商)”最低求助积分说明 809073