Road scenes segmentation across different domains by disentangling latent representations

HIGHLIGHTS

• who: Francesco Barbato from the Department of Information Engineering, University of Padova, Via Gradenigo, b, Padova, Italy have published the paper: Road scenes segmentation across different domains by disentangling latent representations, in the Journal: (JOURNAL)
• what: The authors design and carefully analyze multiple latent space-shaping regularization strategies that work together to reduce the domain shift. The authors propose a novel evaluation metric to capture the relative performance of an adapted model with respect to supervised training. The authors propose an approach focusing on feature space adaptation, introducing a new set of strategies working at . . .
  

   

  

  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.