Adaptive Contrastive Learning with Label Consistency for Source Data Free Unsupervised Domain Adaptation

Xuejun Zhao, Rafal Stanislawski, Paolo Gardoni, Maciej Sulowicz, Adam Glowacz, Grzegorz Krolczyk, Zhixiong Li

Research output: Contribution to journalArticlepeer-review


Unsupervised domain adaptation, which aims to alleviate the domain shift between source domain and target domain, has attracted extensive research interest; however, this is unlikely in practical application scenarios, which may be due to privacy issues and intellectual rights. In this paper, we discuss a more challenging and practical source-free unsupervised domain adaptation, which needs to adapt the source domain model to the target domain without the aid of source domain data. We propose label consistent contrastive learning (LCCL), an adaptive contrastive learning framework for source-free unsupervised domain adaptation, which encourages target domain samples to learn class-level discriminative features. Considering that the data in the source domain are unavailable, we introduce the memory bank to store the samples with the same pseudo label output and the samples obtained by clustering, and the trusted historical samples are involved in contrastive learning. In addition, we demonstrate that LCCL is a general framework that can be applied to unsupervised domain adaptation. Extensive experiments on digit recognition and image classification benchmark datasets demonstrate the effectiveness of the proposed method.

Original languageEnglish (US)
Article number4238
Issue number11
StatePublished - Jun 1 2022


  • unsupervised domain adaptation
  • source free domain adaptation
  • contrastive learning

ASJC Scopus subject areas

  • Analytical Chemistry
  • Information Systems
  • Atomic and Molecular Physics, and Optics
  • Biochemistry
  • Instrumentation
  • Electrical and Electronic Engineering


Dive into the research topics of 'Adaptive Contrastive Learning with Label Consistency for Source Data Free Unsupervised Domain Adaptation'. Together they form a unique fingerprint.

Cite this