中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
DomainVerse: A Benchmark Towards Real-World Distribution Shifts for Training-Free Adaptive Domain Generalization

文献类型：期刊论文

作者Hou, Feng3,4; Yuan, Jin1,5; Yang, Ying6; Zhang, Yao6; Liu, Yang3,4; Zhang, Yang6; Zhong, Cheng6; Shi, Zhongchao6; Fan, Jianping6; He, Zhiqiang2,3,4
刊名IEEE TRANSACTIONS ON MULTIMEDIA
出版日期2025
卷号27页码:6648-6660
关键词Adaptation models Training Benchmark testing Picture archiving and communication systems Data models Image color analysis Computational modeling Data mining Training data Painting DomainVerse training-free adaptive domain generalization vision-language models
ISSN号1520-9210
DOI10.1109/TMM.2025.3586108
英文摘要Traditional cross-domain tasks, including unsupervised domain adaptation (UDA), domain generalization (DG) and test-time adaptation (TTA), rely heavily on the training model by source domain data whether for specific or arbitrary target domains. With the recent advance of vision-language models (VLMs), recognized as natural source models that can be transferred to various downstream tasks without any parameter training, we propose a novel cross-domain task directly combining the strengths of both UDA and DG, named Training-Free Adaptive Domain Generalization (TF-ADG). However, current cross-domain datasets have many limitations, such as unrealistic domains, unclear domain definitions, and the inability to fine-grained domain decomposition, which hinder the real-world application of current cross-domain models due to the lack of accurate and fair evaluation of fine-grained realistic domains. These insights motivate us to establish a novel realistic benchmark for TF-ADG. Benefiting from the introduced hierarchical definition of domain shifts, our proposed dataset DomainVerse addresses these issues by providing about 0.5 million images from 390 realistic, hierarchical, and balanced domains, allowing for decomposition across multiple domains within each image. With the help of the constructed DomainVerse and VLMs, we further propose two algorithms called Domain CLIP and Domain++ CLIP for training-free adaptive domain generalization. Extensive and comprehensive experiments demonstrate the significance of the dataset and the effectiveness of the proposed methods.
资助项目AI Lab ; Lenovo Research
WOS研究方向Computer Science ; Telecommunications
语种英语
WOS记录号WOS:001579069300018
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
源URL[http://119.78.100.204/handle/2XEOYT63/41672]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Zhang, Yao; He, Zhiqiang
作者单位1.Southeast Univ, Key Lab Comp Network & Informat Integrat, Minist Educ, Nanjing 211189, Peoples R China
2.Lenovo Ltd, Beijing 100000, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Beijing 100000, Peoples R China
4.Univ Chinese Acad Sci, Beijing 100000, Peoples R China
5.Southeast Univ, Sch Comp Sci & Engn, Minist Educ, Nanjing 211189, Peoples R China
6.Lenovo Res, AI Lab, Beijing 100000, Peoples R China
推荐引用方式
GB/T 7714		 Hou, Feng,Yuan, Jin,Yang, Ying,et al. DomainVerse: A Benchmark Towards Real-World Distribution Shifts for Training-Free Adaptive Domain Generalization[J]. IEEE TRANSACTIONS ON MULTIMEDIA,2025,27:6648-6660.
APA Hou, Feng.,Yuan, Jin.,Yang, Ying.,Zhang, Yao.,Liu, Yang.,...&Rui, Yong.(2025).DomainVerse: A Benchmark Towards Real-World Distribution Shifts for Training-Free Adaptive Domain Generalization.IEEE TRANSACTIONS ON MULTIMEDIA,27,6648-6660.
MLA Hou, Feng,et al."DomainVerse: A Benchmark Towards Real-World Distribution Shifts for Training-Free Adaptive Domain Generalization".IEEE TRANSACTIONS ON MULTIMEDIA 27(2025):6648-6660.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。