arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.02714cs.CV
收藏

DomainVerse:面向真实世界分布偏移的免调优自适应域泛化基准

DomainVerse: A Benchmark Towards Real-World Distribution Shifts For Tuning-Free Adaptive Domain Generalization

Institute of Computing Technology (ICT), Chinese Academy of Sciences(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学);Southeast University(东南大学);Lenovo Research(联想研究院);Lenovo Ltd.(联想有限公司)

Feng Hou, Jin Yuan, Ying Yang, Yang Liu, Yang Zhang, Cheng Zhong, Zhongchao Shi, Jianping Fan, Yong Rui, Zhiqiang He

AI总结:

针对自适应域泛化缺乏真实细粒度基准的问题,本文构建含390个真实域、约50万张图像的DomainVerse,并提出免调优的Domain CLIP与Domain++ CLIP方法。

摘要:

包括域适应和域泛化在内的传统跨域任务,严重依赖利用源域数据训练模型。随着视觉-语言模型(VLM)近期取得进展,它们被视为天然的源模型,跨域任务随之转变为:在具备先验域知识的情况下,将预训练源模型直接适配到任意目标域;我们将该任务命名为自适应域泛化(ADG)。然而,当前跨域数据集存在诸多局限,例如域不真实、域定义不清晰以及无法进行细粒度域分解,这促使我们为 ADG 构建一个名为 DomainVerse 的新型数据集。得益于所引入的域偏移层次化定义,DomainVerse 包含来自 390 个细粒度真实域的约 50 万张图像。借助构建的 DomainVerse 和 VLM,我们提出了两种用于免调优自适应域泛化的方法,分别称为 Domain CLIP 和 Domain++ CLIP。广泛而全面的实验证明了该数据集的重要意义以及所提方法的有效性。

英文摘要:

Traditional cross-domain tasks, including domain adaptation and domain generalization, rely heavily on training model by source domain data. With the recent advance of vision-language models (VLMs), viewed as natural source models, the cross-domain task changes to directly adapt the pre-trained source model to arbitrary target domains equipped with prior domain knowledge, and we name this task Adaptive Domain Generalization (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 drives us to establish a novel dataset DomainVerse for ADG. Benefiting from the introduced hierarchical definition of domain shifts, DomainVerse consists of about 0.5 million images from 390 fine-grained realistic domains. With the help of the constructed DomainVerse and VLMs, we propose two methods called Domain CLIP and Domain++ CLIP for tuning-free adaptive domain generalization. Extensive and comprehensive experiments demonstrate the significance of the dataset and the effectiveness of the proposed methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑