Combating label noise in image data using multinet flexible confident learning

HIGHLIGHTS

• who: Adam Popowicz and collaborators from the Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology have published the research work: Combating Label Noise in Image Data Using MultiNET Flexible Confident Learning, in the Journal: (JOURNAL) of 29/06/2022
• what: The authors propose a novel method for the automatic detection of noisy labels within image datasets. is an adaptation of the current state-of-the-art learning method. As in other work, the approach focuses on the increase in the classification performance of the final DNN model, which was shown to . . .
  

   

  

  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.