Breast mass detection with faster r-cnn: on the feasibility of learning from noisy annotations

HIGHLIGHTS

• who: SINA FAMOURI and colleagues from the Department of Computer Control Engineering, Politecnico di Torino, Turin, Italy have published the Article: Breast Mass Detection With Faster R-CNN: On the Feasibility of Learning From Noisy Annotations, in the Journal: (JOURNAL)
• what: The authors provide here a quantitative evaluation of the effect of bounding box coordinate noise on the performance of Faster R-CNN object detection networks for breast mass detection. The authors show how due to an imperfect matching between the ground truth the network bounding box proposals the noise is propagated during training reduces . . .
  

   

  

  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.