End-To-End Training of Neural Networks with Topological Loss

This video program is a part of the Premium package:

End-To-End Training of Neural Networks with Topological Loss


  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

End-To-End Training of Neural Networks with Topological Loss

0 views
  • Share
Create Account or Sign In to post comments
We present a topological loss to train neural networks to segmentation fine structures with correct topology. The differentiable loss enforces the topology of the segmentation and the ground truth to be similar, based on the theory of persistent homology. The learnt network consistently outperform other methods in metrics relevant to structural accuracy. We also discuss applications of the method to other learning tasks.
We present a topological loss to train neural networks to segmentation fine structures with correct topology. The differentiable loss enforces the topology of the segmentation and the ground truth to be similar, based on the theory of persistent homology. The learnt network consistently outperform other methods in metrics relevant to structural accuracy. We also discuss applications of the method to other learning tasks.