Google Inc.

Yukun Zhu

Xuhui Jia

Bradley Ray Green

Hartwig Adam

Yossi Matias

Colvin Pitts

Jonathon Shlens

Barret Zoph

Michael Rubinstein

Marius Renn

Chun-Te Chu

Inbar Mosseri

Gerhard Florian Schroff

Liang-Chieh Chen

Benjamin Schlesinger

Noam Etzion-Rosenberg

Amit Pitaru

Oran Lang

Ariel Ephrat

Kai Han

Anatoly Efros

Georgios Papandreou

Maxwell Donald Emmet Collins

Israel Or Weinstein

Yandong Li

Yu-Chuan Su

Yang Zhao

Tal Remez

Stella Laurenzo

Systems and methods for providing deep learning models capable of performing joint representation learning and new category discovery on a mixture of labeled and unlabeled data, which may include single- and multi-modal data. In some examples, a flexible end-to-end framework uses unified contrastive learning on labeled and unlabeled data based on both instance discrimination and category discrimination, and further uses Winner-Take-All hashing to generate a pseudo-label based on the similarity between each pair of unlabeled data points that can be used to train the model to generate clustering assignments for each unlabeled data point. In some examples, the unified contrastive learning may be further based on cross-modal discrimination.

Flexible framework for joint representation learning and unknown category discovery

Systems and methods for training a restoration model can leverage training for two sub-tasks to train the restoration model to generate realistic and identity-preserved outputs. The systems and methods can balance the training of the generation task and the reconstruction task to ensure the generated outputs preserve the identity of the original subject while generating realistic outputs. The systems and methods can further leverage a feature quantization model and skip connections to improve the model output and overall training.

Training a restoration model for balanced generation and reconstruction

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio-visual speech separation. A method includes: receiving, by a user device, a first indication of one or more first speakers visible in a current view recorded by a camera of the user device, in response, generating a respective isolated speech signal for each of the one or more first speakers that isolates speech of the first speaker in the current view and sending the isolated speech signals for each of the one or more first speakers to a listening device operatively coupled to the user device, receiving, by the user device, a second indication of one or more second speakers visible in the current view recorded by the camera of the user device, and in response generating and sending a respective isolated speech signal for each of the one or more second speakers to the listening device.

Audio-visual hearing aid

A computing system and method that can be used for safe and privacy preserving video representations of participants in a videoconference. In particular, the present disclosure provides a general pipeline for generating reconstructions of videoconference participants based on semantic statuses and/or activity statuses of the participants. The systems and methods of the present disclosure allow for videoconferences that convey necessary or meaningful information of participants through presentation of generalized representations of participants while filtering unnecessary or unwanted information from the representations by leveraging machine-learning models.

Safe and privacy preserving video representation

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes obtaining training data for a dense image prediction task; and determining an architecture for a neural network configured to perform the dense image prediction task, comprising: searching a space of candidate architectures to identify one or more best performing architectures using the training data, wherein each candidate architecture in the space of candidate architectures comprises (i) the same first neural network backbone that is configured to receive an input image and to process the input image to generate a plurality of feature maps and (ii) a different dense prediction cell configured to process the plurality of feature maps and to generate an output for the dense image prediction task; and determining the architecture for the neural network based on the best performing candidate architectures.

Neural architecture search for dense image prediction tasks

Growing community of inventors

Shoreline, WA, United States of America

Yukun Zhu