Active learning-driven siamese network for few-shot hyperspectral image classification

HIGHLIGHTS

• who: Xiyao Di and collaborators from the School of Earth Sciences and Engineering, Hohai University, Nanjing, China have published the paper: Active Learning-Driven Siamese Network for Few-Shot Hyperspectral Image Classification, in the Journal: (JOURNAL)
• what: In this paper an active learning-based siamese network (ALSN) is proposed to solve the limited labeled samples problem in HSI First the authors designed a dual learning-based siamese network (DLSN) which consists of a contrastive learning module and a module. The authors focused on the quality of the original input. The authors propose an adversarial uncertainty . . .
  

   

  

  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.