Google Inc.

Yonglong Tian

Ce Liu

Dilip Krishnan

Chen Wang

Aaron Joseph Maschinot

Aaron Yehuda Sarna

Piotr Teterwak

Prannay Khosla

Phillip John Isola

Philip John Isola

The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.

Supervised contrastive learning with multiple positive examples

Growing community of inventors

Cambridge, MA, United States of America

Yonglong Tian