Generalization of vision pre-trained models for histopathology

HIGHLIGHTS

• who: Milad Sikaroudi from the University of Waterloo, Waterloo, ON, Canada have published the paper: Generalization of vision pre-trained models for histopathology, in the Journal: Scientific Reports Scientific Reports
• what: In the context of OOD generalization, the authors show that even though pre-training on large datasets is critical (Semi-Weakly Supervised Learning (SWSL)25 and Semi-Supervised Learning (SSL)25 versus vanilla u00adImageNet26 pre-trained model), the nature of the pre-trained model is crucial as well u00ad(KimiaNet27 vs. u00adSWSL25 and u00adSSL25). The authors investigate these types of pre-trained models to . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or Email

  Password

  Remember me

  Lost your password?

  If you don't have an account, you can create one here.