Cross-domain few-shot learning based on pseudo-siamese neural network

HIGHLIGHTS

• who: Yuxuan Gong from the SchoolNormal University have published the article: Cross-domain few-shot learning based on pseudo-Siamese neural network, in the Journal: Scientific Reports Scientific Reports
• what: The authors propose a training method that extracts the contour features of the samples and sends the original samples and the extracted features to the two branches of the neural_network separately. For the network proposed in this paper, the heatmap analysis of the pre-training and meta-learning process is carried out to intuitively illustrate the feasibility of the network. In this paper, based on . . .
  

   

  

  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.