Leveraging Mixture Alignment for Multi-Source Domain Adaptation

计算机科学 适应(眼睛) 领域(数学分析) 人工智能 模式识别(心理学) 数学 光学 物理 数学分析
作者
Aveen Dayal,S. Shrusti,Linga Reddy Cenkeramaddi,Chalavadi Krishna Mohan,Abhinav Kumar
出处
期刊:IEEE transactions on image processing [Institute of Electrical and Electronics Engineers]
卷期号:34: 885-898 被引量:30
标识
DOI:10.1109/tip.2025.3532094
摘要

In a conventional Domain Adaptation (DA) setting, we only have one source and target domain, whereas, in many real-world applications, data is often collected from several related sources in different conditions. This has led to a more practical and challenging knowledge transfer problem called Multi-source Domain Adaptation (MDA). Several methodologies, such as prototype matching, explicit distance discrepancy, adversarial learning, etc., have been considered to tackle the MDA problem in recent years. Among them, the adversarial-based learning framework is a popular methodology for transferring knowledge from multiple sources to target domains using a minmax optimization strategy. Despite the advances in adversarial-based methods, several limitations exist, such as the need for a classifier-aware discrepancy metric to align the domains and the need to consider target samples' consistency and semantic information while aligning the domains. To mitigate these issues, in this work, we propose a novel adversarial learning MDA algorithm, MDAMA, which aligns the target domain with a mixture distribution that consists of source domains. MDAMA uses margin-based discrepancy and augmented intermediate distributions to align the domains effectively. We also propose consistency of target samples by confidence thresholding and transfer of semantic information from multiple source domains to the augmented target domain to further improve the performance of the target domain. We extensively experiment with the MDAMA algorithm on popular real-world MDA datasets such as OfficeHome, Office31, PACS, Office-Caltech, and DomainNet. We evaluate the MDAMA model on these benchmark datasets and demonstrate top performance in all of them.
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
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
研友_841dlL发布了新的文献求助10
1秒前
1秒前
1秒前
xi完成签到,获得积分10
1秒前
果果完成签到,获得积分10
1秒前
小雨点完成签到,获得积分20
1秒前
tomorrow完成签到,获得积分10
1秒前
负责的数据线完成签到,获得积分10
2秒前
王京华完成签到,获得积分10
2秒前
莫等闲完成签到,获得积分0
2秒前
2秒前
简单刺猬完成签到,获得积分10
2秒前
Emily完成签到,获得积分10
2秒前
JamesPei的应助被冷艳的熊猫采纳,获得10
2秒前
酷波er的应助被hetao286采纳,获得10
3秒前
香蕉静芙完成签到,获得积分10
3秒前
段YY发布了新的文献求助10
3秒前
可靠的代胜完成签到,获得积分10
4秒前
顺心的谷菱完成签到,获得积分10
4秒前
newmoon完成签到 ,获得积分10
5秒前
爱吃泡芙完成签到,获得积分10
5秒前
Researcher发布了新的文献求助10
5秒前
YXQ完成签到,获得积分10
5秒前
啦啦啦完成签到 ,获得积分10
6秒前
wyy完成签到,获得积分10
6秒前
随缘完成签到 ,获得积分10
6秒前
初a完成签到,获得积分10
8秒前
任性的冰露完成签到,获得积分10
8秒前
动人的三颜完成签到,获得积分10
9秒前
baijie完成签到 ,获得积分10
9秒前
研友_841dlL完成签到,获得积分10
9秒前
兔子爱吃胡萝卜完成签到,获得积分10
9秒前
xxy完成签到,获得积分20
9秒前
Cheney完成签到,获得积分10
9秒前
活泼红牛完成签到,获得积分10
9秒前
10秒前
molly完成签到,获得积分10
10秒前
赵亚南完成签到,获得积分10
10秒前
李李玲完成签到,获得积分10
10秒前
莉丽完成签到,获得积分10
11秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
八旗制度の研究 600
plantTFDB 508
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8173463
求助须知:如何正确求助?哪些是违规求助? 9565690
关于积分的说明 21781315
捐赠科研通 7767647
什么是DOI,文献DOI怎么找? 3431597
关于科研通互助平台的介绍 2555855
邀请新用户注册赠送积分活动 2476808