Lovasz-Softmax
Description
The Lovasz-Softmax loss is a loss function for multiclass semantic segmentation that incorporates the softmax operation in the Lovasz extension. The Lovasz extension is a means by which we can achieve direct optimization of the mean intersection-over-union loss in neural networks.
Papers Using This Method
Adversarial Multiscale Feature Learning for Overlapping Chromosome Segmentation2020-12-22Optimization for Medical Image Segmentation: Theory and Practice when evaluating with Dice Score or Jaccard Index2020-10-26TORNADO-Net: mulTiview tOtal vaRiatioN semAntic segmentation with Diamond inceptiOn module2020-08-24SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving2020-03-07The Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks2018-06-01