 |
Conference papers
On power Jaccard losses for semantic segmentation
Abstract : In this work, a new generalized loss function is proposed called power Jaccard to perform semantic segmentation tasks. It is compared with classical loss functions in different scenarios, including gray level and color image segmentation, as well as 3D point cloud segmentation. The results show improved performance, stability and convergence. We made available the code with our proposal with a demonstrative example.
https://hal.archives-ouvertes.fr/hal-03139997
Contributor : David Duque <>
Submitted on : Friday, February 12, 2021 - 2:18:36 PM
Last modification on : Sunday, February 28, 2021 - 3:08:07 AM
Contributor : David Duque <>
Submitted on : Friday, February 12, 2021 - 2:18:36 PM
Last modification on : Sunday, February 28, 2021 - 3:08:07 AM
File
On_Power_losses_for_semantic_s...
Files produced by the author(s)