US Patent Issued to KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION on Dec. 30 for "Deep learning-based method for improving feature map compression efficiency" (South Korean Inventors)

ALEXANDRIA, Va., Dec. 31 -- United States Patent no. 12,513,317, issued on Dec. 30, was assigned to KWANGWOON UNIVERSITY INDUSTRY-ACADEMIC COLLABORATION FOUNDATION (Seoul, South Korea).

"Deep learning-based method for improving feature map compression efficiency" was invented by Dong Gyu Sim (Seoul, South Korea) and Na Seong Kwon (Seoul, South Korea).

According to the abstract* released by the U.S. Patent & Trademark Office: "The present disclosure may be a deep learning-based method for improving feature map compression efficiency, wherein feature maps can be selectively transmitted from an encoder, and untransmitted feature maps can be predicted and generated after restoring the image quality of the transmitted feature maps using a deep...