Adaptive contrastive learning with label consistency for source data free unsupervised domain adaptation

HIGHLIGHTS

• who: Xuejun Zhao et al. from the Department of Electrical, Control and Computer Engineering, Opole University of Technology have published the article: Adaptive Contrastive Learning with Label Consistency for Source Data Free Unsupervised Domain Adaptation, in the Journal: Sensors 2022, 22, 4238. of /2022/
• what: The authors propose label consistent contrastive learning (LCCL) an contrastive learning framework for source-free adaptation which encourages target samples to learn class-level discriminative features. The authors demonstrate that LCCL is a general framework that can be applied to Extensive experiments on digit recognition and image classification benchmark datasets . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.