Graphical Modeling for Multi-Source Domain Adaptation

计算机科学 域适应 图形模型 适应(眼睛) 人工智能 领域(数学分析) 分类器(UML) 数学 数学分析 物理 光学
作者
Minghao Xu,Hang Wang,Bingbing Ni
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:46 (3): 1727-1741 被引量:12
标识
DOI:10.1109/tpami.2022.3172372
摘要

Multi-Source Domain Adaptation (MSDA) focuses on transferring the knowledge from multiple source domains to the target domain, which is a more practical and challenging problem compared to the conventional single-source domain adaptation. In this problem, it is essential to model multiple source domains and target domain jointly, and an effective domain combination scheme is also highly required. The graphical structure among different domains is useful to tackle these challenges, in which the interdependency among various instances/categories can be effectively modeled. In this work, we propose two types of graphical models, i.e. C onditional R andom F ield for MSDA ( CRF-MSDA ) and M arkov R andom F ield for MSDA ( MRF-MSDA ), for cross-domain joint modeling and learnable domain combination. In a nutshell, given an observation set composed of a query sample and the semantic prototypes ( i.e. representative category embeddings) on various domains, the CRF-MSDA model seeks to learn the joint distribution of labels conditioned on the observations. We attain this goal by constructing a relational graph over all observations and conducting local message passing on it. By comparison, MRF-MSDA aims to model the joint distribution of observations over different Markov networks via an energy-based formulation, and it can naturally perform label prediction by summing the joint likelihoods over several specific networks. Compared to the CRF-MSDA counterpart, the MRF-MSDA model is more expressive and possesses lower computational cost. We evaluate these two models on four standard benchmark data sets of MSDA with distinct domain shift and data complexity, and both models achieve superior performance over existing methods on all benchmarks. In addition, the analytical studies illustrate the effect of different model components and provide insights about how the cross-domain joint modeling performs.
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
yxr0315发布了新的文献求助10
刚刚
Hello应助陈曦采纳,获得10
1秒前
如意枫叶发布了新的文献求助10
2秒前
慕青应助蝈蝈采纳,获得10
2秒前
3秒前
4秒前
王小西发布了新的文献求助10
5秒前
5秒前
6秒前
四木完成签到,获得积分10
6秒前
7秒前
努力完成签到,获得积分10
7秒前
小当家发布了新的文献求助10
8秒前
9秒前
帅气冰菱发布了新的文献求助10
9秒前
Dino发布了新的文献求助10
11秒前
12秒前
蝈蝈完成签到,获得积分10
12秒前
12秒前
淡定的松子完成签到,获得积分10
13秒前
帅男发布了新的文献求助10
13秒前
Owen应助科研通管家采纳,获得10
14秒前
JamesPei应助科研通管家采纳,获得10
14秒前
14秒前
科研通AI5应助科研通管家采纳,获得10
14秒前
14秒前
半城微凉应助科研通管家采纳,获得10
14秒前
小蘑菇应助科研通管家采纳,获得10
14秒前
cherlie应助科研通管家采纳,获得10
14秒前
Owen应助科研通管家采纳,获得30
14秒前
科研通AI5应助科研通管家采纳,获得10
14秒前
安详立果发布了新的文献求助10
14秒前
充电宝应助科研通管家采纳,获得10
15秒前
wdy111应助科研通管家采纳,获得10
15秒前
田様应助科研通管家采纳,获得20
15秒前
小二郎应助科研通管家采纳,获得10
15秒前
Hollow发布了新的文献求助10
15秒前
丘比特应助科研通管家采纳,获得10
15秒前
JamesPei应助科研通管家采纳,获得10
15秒前
共享精神应助科研通管家采纳,获得10
15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 3989589
求助须知:如何正确求助?哪些是违规求助? 3531795
关于积分的说明 11254881
捐赠科研通 3270329
什么是DOI,文献DOI怎么找? 1804966
邀请新用户注册赠送积分活动 882136
科研通“疑难数据库(出版商)”最低求助积分说明 809176