US Patent Issued to GOOGLE on March 24 for "Systems and methods for training multi-class object classification models with partially labeled training data" (California, Texas Inventors)

ALEXANDRIA, Va., March 24 -- United States Patent no. 12,586,349, issued on March 24, was assigned to GOOGLE LLC (Mountain View, Calif.).

"Systems and methods for training multi-class object classification models with partially labeled training data" was invented by Huizhong Chen (Mountain View, Calif.), Zhichao Lu (Santa Clara, Calif.) and Jonathan Zwi Ben-Meshulam (Fort Worth, Texas).

According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods of the present disclosure are directed to a computer-implemented method for training a machine-learned multi-class object classification model with partially labeled training data. The method can include obtaining image data depicting objects and ground truth da...