Self-supervised encoders are better transfer learners in remote sensing applications

HIGHLIGHTS

• who: Zachary D. Calhoun et al. from the Department of Civil and Environmental Engineering, Duke University, Hudson Hall, Science Dr, Durham, NC, USA have published the paper: Self-Supervised Encoders Are Better Transfer Learners in Remote Sensing Applications, in the Journal: (JOURNAL)
• what: The authors show that an encoder pre-trained on ImageNet using selfsupervision transfers than one pre-trained using supervision on three diverse remote sensing applications. The authors seek to explore this paradigm further using three distinct remote sensing datasets. The authors seek to test this paradigm using a less computationally expensive self . . .
  

   

  

  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.