US Patent Issued to Salesforce on Nov. 11 for "Systems and methods for noise-robust contrastive learning" (Singaporean Inventors)

ALEXANDRIA, Va., Nov. 11 -- United States Patent no. 12,468,952, issued on Nov. 11, was assigned to Salesforce Inc. (San Francisco).

"Systems and methods for noise-robust contrastive learning" was invented by Junnan Li (Singapore) and Chu Hong Hoi (Singapore).

According to the abstract* released by the U.S. Patent & Trademark Office: "Embodiments described herein provide systems and methods for noise-robust contrastive learning. In view of the need for a noise-robust learning system, embodiments described herein provides a contrastive learning mechanism that combats noise by learning robust representations of the noisy data samples. Specifically, the training images are projected into a low-dimensional subspace, and the geometric structur...