On power Jaccard losses for semantic segmentation - Morphologie mathématique (CMM) Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

On power Jaccard losses for semantic segmentation

Jean-Emmanuel Deschaud
Francois Goulette
Andrés Serna

Résumé

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.
Fichier principal
Vignette du fichier
On_Power_losses_for_semantic_segmentation.pdf (1.02 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03139997 , version 1 (12-02-2021)

Identifiants

  • HAL Id : hal-03139997 , version 1

Citer

David Duque-Arias, Santiago Velasco-Forero, Jean-Emmanuel Deschaud, Francois Goulette, Andrés Serna, et al.. On power Jaccard losses for semantic segmentation. VISAPP 2021 : 16th International Conference on Computer Vision Theory and Applications, Feb 2021, Vienne (on line), Austria. ⟨hal-03139997⟩
5063 Consultations
1007 Téléchargements

Partager

Gmail Facebook X LinkedIn More