Google Inc.

Piotr Teterwak

Ce Liu

Dilip Krishnan

Aaron Joseph Maschinot

Aaron Yehuda Sarna

Chen Wang

Prannay Khosla

Yonglong Tian

Jingbin Wang

Mikael Bonnevie

Michael Krainin

Hossein Talebi

Phillip John Isola

Philip John Isola

Shuchao Bi

Wenchao Tong

Haifeng Gong

Raanan Sayag

Michael Spencer Krainin

Mikael Pierre Bonnevie

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

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating realistic extensions of images. In one aspect, a method comprises providing an input that comprises a provided image to a generative neural network having a plurality of generative neural network parameters. The generative neural network processes the input in accordance with trained values of the plurality of generative neural network parameters to generate an extended image. The extended image has (i) more rows, more columns, or both than the provided image, and (ii) is predicted to be a realistic extension of the provided image. The generative neural network is trained using an adversarial loss objective function.

Image extension neural networks

Growing community of inventors

Boston, MA, United States of America

Piotr Teterwak