US Patent Issued to Tencent Technology (Shenzhen) on April 29 for "Using training images and scaled training images to train an image segmentation model" (Chinese Inventors)

ALEXANDRIA, Va., June 9 -- United States Patent no. 12,288,383, issued on April 29, was assigned to Tencent Technology (Shenzhen) Co. Ltd. (Shenzhen, China).

"Using training images and scaled training images to train an image segmentation model" was invented by Donghuan Lu (Shenzhen, China), Kai Ma (Shenzhen, China) and Yefeng Zheng (Shenzhen, China).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for training an image segmentation model includes calling an encoder to perform feature extraction on a sample image and a scale image to obtain a sample image feature and a scale image feature. The method also includes performing a class activation graph calculation to obtain a sample class activation graph...