The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Aug. 27, 2024
Filed:
May. 21, 2021
Toyota Jidosha Kabushiki Kaisha, Toyota Aichi-ken, JP;
Katholieke Universiteit Leuven, Leuven, BE;
Wim Abbeloos, Hove, BE;
Gabriel Othmezouri, Ixelles, BE;
Wouter Van Gansbeke, Dilbeek, BE;
Simon Vandenhende, Leuven, BE;
Marc Proesmans, Lede, BE;
Stamatios Georgoulis, Zurich, CH;
Luc Van Gool, Zurich, CH;
TOYOTA JIDOSHA KABUSHIKI KAISHA, Toyota Aichi-ken, JP;
KATHOLIEKE UNIVERSITEIT LEUVEN, Leuven, BE;
Abstract
A computer-implemented method for training a classifier (Φη), including: training a pretext model (ΦΘ) to learn a pretext task, so as to minimize a distance between an output of a source sample via the pretext model (ΦΘ) and an output of a corresponding transformed sample via the pretext model (ΦΘ), the transformed sample being a sample obtained by applying a transformation (T) to the source sample; S) determining a neighborhood (NXi) of samples (Xi) of a dataset (SD) in the embedding space; S) training the classifier (Φη) to predict respective estimated probabilities Φηj(Xi), j=1 . . . C, for a sample (Xi) to belong to respective clusters (Cj), by using a second training criterion which tends to: maximize a likelihood for a sample and its neighbors (Xj) of its neighborhood (Nxi) to belong to the same cluster; and force the samples to be distributed over several clusters.