Hyperspectral image classification with pre-activation residual attention network

HIGHLIGHTS

• who: HONGMIN GAO et al. from the of Computer Information, Hohai University, Nanjing, China have published the paper: Hyperspectral Image Classification With Pre-Activation Residual Attention Network, in the Journal: (JOURNAL)
• what: The authors compare the method with the SVM and several state-of-the-art CNN-based methods, including DCNN , DFFN and SSRN . The main reason is that they are equipped with deep architecture, which enables them to learn high-level discriminative features of HSIs. The authors propose a pre-activation residual attention network, that incorporates both spectral and spatial information, for hyperspectral image . . .
  

   

  

  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.