Leland Stanford Junior University

Toyota Research Institute, Inc.

Tengyu Ma

Adrien David Gaidon

Colin Wei

Jeff Z Haochen

A method for self-supervised learning is described. The method includes generating a plurality of augmented data from unlabeled image data. The method also includes generating a population augmentation graph for a class determined from the plurality of augmented data. The method further includes minimizing a contrastive loss based on a spectral decomposition of the population augmentation graph to learn representations of the unlabeled image data. The method also includes classifying the learned representations of the unlabeled image data to recover ground-truth labels of the unlabeled image data.

Growing community of inventors

Stanford, CA, United States of America

Tengyu Ma