Going beyond p-Convolutions to Learn Grayscale Morphological Operators - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Going beyond p-Convolutions to Learn Grayscale Morphological Operators

Résumé

Integrating mathematical morphology operations within deep neural networks has been subject to increasing attention lately. However, replacing standard convolution layers with erosions or dilations is particularly challenging because the min and max operations are not differentiable. Relying on the asymptotic behavior of the counter-harmonic mean, p-convolutional layers were proposed as a possible workaround to this issue since they can perform pseudo-dilation or pseudo-erosion operations (depending on the value of their inner parameter p), and very promising results were reported. In this work, we present two new morphological layers based on the same principle as the p-convolutional layer while circumventing its principal drawbacks, and demonstrate their potential interest in further implementations within deep convolutional neural network architectures.

Dates et versions

hal-04579608 , version 1 (17-05-2024)

Identifiants

Citer

Alexandre Kirszenberg, Guillaume Tochon, Élodie Puybareau, Jesus Angulo. Going beyond p-Convolutions to Learn Grayscale Morphological Operators. Proceedings of the IAPR International Conference on Discrete Geometry and Mathematical Morphology (DGMM), May 2021, Uppsala, Sweden. pp.470--482, ⟨10.1007/978-3-030-76657-3_34⟩. ⟨hal-04579608⟩
14 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More