ALEXANDRIA, Va., June 5 -- United States Patent no. 12,277,696, issued on April 15, was assigned to Robert Bosch GmbH (Germany).
"Data augmentation for domain generalization" was invented by Laura Beggel (Stuttgart, Germany), Filipe J. Cabrita Condessa (Pittsburgh), Robin Hutmacher (Renningen, Germany), Jeremy Kolter (Pittsburgh), Nhung Thi Phuong Ngo (Karlsruhe, Germany), Fatemeh Sheikholeslami (Pittsburgh) and Devin T. Willmott (Pittsburgh).
According to the abstract* released by the U.S. Patent & Trademark Office: "Methods and systems are disclosed for generating training data for a machine learning model for better performance of the model. A source image is selected from an image database, along with a target image. An image segmente...