US Patent Issued to ADOBE on July 7 for "Data attribution for diffusion models" (Pennsylvania, California Inventors)

ALEXANDRIA, Va., July 7 -- United States Patent no. 12,675,976, issued on July 7, was assigned to ADOBE INC. (San Jose, Calif.).

"Data attribution for diffusion models" was invented by Sheng-Yu Wang (Pittsburgh), Alexei A. Efros (Berkeley, Calif.), Junyan Zhu (Pittsburgh) and Richard Zhang (Burlingame, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments of the present disclosure perform training attribution by identifying a synthesized image and a training image, where the synthesized image was generated by an image generation model that was trained with the training image. A machine learning model computes first attribution features for the synthesized image using a first mapping layer and sec...