US Patent Issued to BULL, UNIVERSITE GRENOBLE ALPES, INSTITUT POLYTECHNIQUE DE GRENOBLE, CENTRE NATIONAL DE LA RECHERCHE SCIENTIFQUE on July 14 for "Method, computer program and device for training a dynamic-architecture convolutional neural network for semantic image segmentation" (French Inventors)

ALEXANDRIA, Va., July 14 -- United States Patent no. 12,682,219, issued on July 14, was assigned to BULL SAS (Les Clayes-sous-Bois, France), UNIVERSITE GRENOBLE ALPES (Saint Martin d'Heres, France), INSTITUT POLYTECHNIQUE DE GRENOBLE (Grenoble, France) and CENTRE NATIONAL DE LA RECHERCHE SCIENTIFQUE (Paris).

"Method, computer program and device for training a dynamic-architecture convolutional neural network for semantic image segmentation" was invented by Loic Pauletto (Grenoble, France) and Massih-Reza Amini (La Terrasse, France).

According to the abstract* released by the U.S. Patent & Trademark Office: "The invention relates to a method for training a dynamic-architecture convolutional neural network for semantic image segmentation, i...