End-to-end roadway disease recognition based on transformer architecture

HIGHLIGHTS

• What: The authors design a model based on which uses MobileNet as the backbone network to simplify the network structure and enables interaction and integration of features through an efficient hybrid encoder which reduces the computational load and does not reduce the accuracy. MobileNet is used as a backbone network for feature extraction and the lightweight improvement is carried out through deep separable convolution and point-by-point convolution, which is possible to reduce the calculation amount without reducing the accuracy, speeds up the model reasoning speed, and makes it better deployed on mobile devices. An efficient . . .
  

   

  

  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.