US Patent Issued to NAVER on Oct. 27 for "Language-based explainability of errors made by computer vision models" (French Inventors)

ALEXANDRIA, Va., Oct. 27 -- United States Patent no. 12,775,844, issued on Oct. 27, was assigned to NAVER Corp. (Gyeonggi-Do, South Korea).

"Language-based explainability of errors made by computer vision models" was invented by Gabriela Csurka Khedari (Meylan, France), Tyler Hayes (Grenoble, France), Diane Larlus (La Tronche, France) and Riccardo Volpi (Grenoble, France).

According to the abstract* released by the U.S. Patent & Trademark Office: "A system includes: a model configured to determine uncertainties of results of a task based on images, respectively; a classification module configured to selectively classify the images into a first category or a second category based on the uncertainties, respectively; an embedding module conf...