Systems and methods for contrastive learning with self-labeling refinement

• Main Authors: ZHOU, Pan, XIONG, Caiming, HOI, Steven
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2022
• Subjects: Databases and Information Systems; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/9806; https://ink.library.smu.edu.sg/context/sis_research/article/10806/viewcontent/2022_US_Patent_Contrastive_Learning.pdf
• Institution: Singapore Management University

Embodiments described herein provide a contrastive learning mechanism with self - labeling refinement , which iteratively employs the network and data themselves to generate more accurate and informative soft labels for contrastive learning . Specifically , the contrastive learning framework includes a self - labeling refinery module to explicitly generate accurate labels , and a momentum mix - up module to increase similarity between a query and its positive , which in turn implicitly improves label accuracy.