US Patent Issued to Adobe on June 2 for "Visual grounding of self-supervised representations for machine learning models utilizing difference attention" (Indian Inventors)

ALEXANDRIA, Va., June 2 -- United States Patent no. 12,646,289, issued on June 2, was assigned to Adobe Inc. (San Jose, Calif.).

"Visual grounding of self-supervised representations for machine learning models utilizing difference attention" was invented by Aishwarya Agarwal (Bengaluru, India), Srikrishna Karanam (Bangalore, India) and Balaji Vasan Srinivasan (Bangalore, India).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure relates to systems, non-transitory computer-readable media, and methods for utilizing difference attention to evaluate and/or train machine learning models. In particular, in some embodiments, the disclosed systems generate, utilizing a machine learning model, a firs...