Enhanced robustness of convolutional networks with a push-pull inhibition layer

HIGHLIGHTS

• who: Nicola Strisciuglio from the Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, Groningen, The Netherlands have published the Article: Enhanced robustness of convolutional networks with a push-pull inhibition layer, in the Journal: (JOURNAL)
• what: The authors propose a new layer for CNNs that increases their robustness to several types of corruptions of the input images. The authors demonstrate that the push -pull layer contributes to a considerable improvement in robustness of classification of corrupted images while maintaining state-of-the-art performance on the original image classification The authors . . .
  

   

  

  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.