arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.14976cs.CVcs.AIcs.LG
收藏

深度基础潜在空间中的无监督域适应

Unsupervised Domain Adaptation within Deep Foundation Latent Spaces

School of Computing and Communications(计算与通信学院);Lancaster University(兰卡斯特大学)

Dmitry Kangin, Plamen Angelov

AI总结:

本文在原型网络框架下研究ViT、Dino-V2等视觉基础模型在无微调条件下解决无监督域适应的能力,证明其优于现有基线并指出仍存在的局限。

摘要:

基于视觉Transformer的基础模型(如ViT或Dino-V2)旨在以极少或无需特征微调的方式解决问题。我们采用原型网络设置,分析此类基础模型在不针对源域或目标域进行微调的情况下,能够在多大程度上解决无监督域适应问题。通过定量分析以及对决策过程的定性解释,我们证明所提出的方法能够优于现有基线,同时也展示了该方法目前尚未解决的局限性。

英文摘要:

The vision transformer-based foundation models, such as ViT or Dino-V2, are aimed at solving problems with little or no finetuning of features. Using a setting of prototypical networks, we analyse to what extent such foundation models can solve unsupervised domain adaptation without finetuning over the source or target domain. Through quantitative analysis, as well as qualitative interpretations of decision making, we demonstrate that the suggested method can improve upon existing baselines, as well as showcase the limitations of such approach yet to be solved.

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。

↑