K-textures, a self-supervised hard clustering deep learning algorithm for satellite image segmentation

HIGHLIGHTS

• who: . and colleagues from the Military Institute of Engineering, Brazil Leipzig University, Germany have published the paper: K-textures, a self-supervised hard clustering deep learning algorithm for satellite image segmentation, in the Journal: (JOURNAL)
• what: The authors compare the obtained classes to the real world in land cover types obtained from MapBiomas to understand the capabilities and limitations of the k-textures model. The aim of this section is to create a differentiable function that can return a binary value of 0 or 1 from a continuous value, to create a binary mask for . . .
  

   

  

  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.