arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2103.16765cs.CV
收藏

基于原型跨域自监督学习的Few-Shot无监督领域自适应

Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation

UC Berkeley(加州大学伯克利分校);Nanjing University(南京大学);Tsinghua University(清华大学)

Xiangyu Yue, Zangwei Zheng, Shanghang Zhang, Yang Gao, Trevor Darrell, Kurt Keutzer, Alberto Sangiovanni Vincentelli

摘要:

无监督领域自适应(UDA)将预测模型从完全标记的源域转移到未标记的目标域。然而,在某些应用中,即使在源域中收集标签也是昂贵的,使得大多数以前的工作不切实际。为了解决这个问题,最近的工作进行了实例跨域自监督学习,然后是一个额外的微调阶段。然而,逐实例的自监督学习仅学习和对齐低级区分特征。在本文中,我们提出了一个端到端的原型跨域自监督学习(PCS)框架的Few-Shot无监督领域自适应(FUDA)。PCS不仅执行跨域低级特征对齐,而且还对跨域共享嵌入空间中的语义结构进行编码和对齐。我们的框架捕捉范畴明智的语义结构的数据域中的原型对比学习,并通过跨域原型自我监督进行功能对齐。与最先进的方法相比,PCS在Office、Vis-Home、VisDA-2017和DomainNet上分别将FUDA上不同领域对的平均分类准确率提高了10.5%、3.5%、9.0%和13.2%。我们的项目页面位于http://xyue.io/pcs-fuda/index.html

英文摘要:

Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive even to collect labels in the source domain, making most previous works impractical. To cope with this problem, recent work performed instance-wise cross-domain self-supervised learning, followed by an additional fine-tuning stage. However, the instance-wise self-supervised learning only learns and aligns low-level discriminative features. In this paper, we propose an end-to-end Prototypical Cross-domain Self-Supervised Learning (PCS) framework for Few-shot Unsupervised Domain Adaptation (FUDA). PCS not only performs cross-domain low-level feature alignment, but it also encodes and aligns semantic structures in the shared embedding space across domains. Our framework captures category-wise semantic structures of the data by in-domain prototypical contrastive learning; and performs feature alignment through cross-domain prototypical self-supervision. Compared with state-of-the-art methods, PCS improves the mean classification accuracy over different domain pairs on FUDA by 10.5%, 3.5%, 9.0%, and 13.2% on Office, Office-Home, VisDA-2017, and DomainNet, respectively. Our project page is at http://xyue.io/pcs-fuda/index.html

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。

↑