arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.04393cs.CVcs.LG
收藏

通用无源领域自适应

Universal Source-Free Domain Adaptation

Indian Institute of Science(印度科学学院)

Jogendra Nath Kundu, Naveen Venkat, Rahul M, R. Venkatesh Babu

摘要:

有一个强烈的动机,以开发通用的学习技术,可以转移的知识,类可分性从一个标记的源域到一个未标记的目标域中存在的域转移。现有的领域自适应(DA)方法由于依赖于源-目标标签-集合关系(如闭集、开集或部分DA)的知识而不适合实际的DA场景。此外,几乎所有先前的无监督DA工作甚至在部署期间都需要源样本和目标样本共存,这使得它们不适合实时适应。没有这种不切实际的假设,我们提出了一种新的两阶段学习过程。1)在采购阶段,我们的目标是为未来的无源部署配备模型,假设没有即将到来的类别差距和域转移的先验知识。为了实现这一点,我们提高了模型的能力,拒绝外的源分布样本,利用现有的源数据,在一个新的生成分类器框架。2)在部署阶段,我们的目标是设计一个统一的适应算法,能够在广泛的类别差距,没有访问以前看到的源样本。为此,与使用复杂的对抗训练机制相比,我们通过利用一种新的实例级加权机制(称为源相似性度量(SSM))定义了一个简单而有效的无源自适应目标。一个彻底的评估表明,所提出的学习框架具有优越的DA性能的实际可用性,即使在国家的最先进的源依赖的方法。

英文摘要:

There is a strong incentive to develop versatile learning techniques that can transfer the knowledge of class-separability from a labeled source domain to an unlabeled target domain in the presence of a domain-shift. Existing domain adaptation (DA) approaches are not equipped for practical DA scenarios as a result of their reliance on the knowledge of source-target label-set relationship (e.g. Closed-set, Open-set or Partial DA). Furthermore, almost all prior unsupervised DA works require coexistence of source and target samples even during deployment, making them unsuitable for real-time adaptation. Devoid of such impractical assumptions, we propose a novel two-stage learning process. 1) In the Procurement stage, we aim to equip the model for future source-free deployment, assuming no prior knowledge of the upcoming category-gap and domain-shift. To achieve this, we enhance the model's ability to reject out-of-source distribution samples by leveraging the available source data, in a novel generative classifier framework. 2) In the Deployment stage, the goal is to design a unified adaptation algorithm capable of operating across a wide range of category-gaps, with no access to the previously seen source samples. To this end, in contrast to the usage of complex adversarial training regimes, we define a simple yet effective source-free adaptation objective by utilizing a novel instance-level weighting mechanism, named as Source Similarity Metric (SSM). A thorough evaluation shows the practical usability of the proposed learning framework with superior DA performance even over state-of-the-art source-dependent approaches.

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。

↑