Federated learning-based yolov8 for face detection

HIGHLIGHTS

• What: The aims of this approach are to enhance privacy protection and minimize data transfer. The aim of this experiment is to integrate the Federated Averaging algorithm into the face recognition model and evaluate the efficacy of the resulting global model. To prevent premature convergence of the model and to effectively showcase the experimental outcomes, a significantly low learning rate of 0.0000001 is employed. The aim of this research is to incorporate joint learning into face detection models using the yolov8 framework training dataset.
• Who: Ruijia Peng from the Department of Computer Science, University . . .
  

   

  

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

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

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