Tolerate failures of the visual camera with robust image classifiers

HIGHLIGHTS

• who: Robust Image Classifiers et al. from the Department of Mathematics Informatics, University of Florence, Florence, Italy have published the article: Tolerate Failures of the Visual Camera With Robust Image Classifiers, in the Journal: (JOURNAL)
• what: This study shows how to build image classifiers that are robust to visual camera failures, so that altered images delivered to the DNN will hardly compromise the image classification task. In Section IV-B the authors describe how the authors created altered images from the clean images of the three datasets. On the left (Fig 4a), the authors show . . .
  

   

  

  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.