公开(公告)号：US12080055B2

公开(公告)日：2024-09-03

申请号：US17697750

申请日：2022-03-17

Applicant: Google LLC

Inventor： Tsung-Yi Lin ,  Barret Zoph ,  Ekin Dogus Cubuk ,  Golnaz Ghiasi ,  Quoc V. Le

IPC: G06V10/82 ,  G06N3/084 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V10/776 ,  G06V10/80

CPC classification number: G06V10/82 ,  G06N3/084 ,  G06V10/764 ,  G06V10/7715 ,  G06V10/774 ,  G06V10/776 ,  G06V10/806

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an image representation neural network.

公开(公告)号：US11847541B2

公开(公告)日：2023-12-19

申请号：US17556871

申请日：2021-12-20

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Quoc V. Le ,  Ekin Dogus Cubuk ,  Barret Zoph

IPC: G06N3/08 ,  G06F18/21 ,  G06F18/214 ,  G06N20/00 ,  G06N3/04

CPC classification number: G06N20/00 ,  G06F18/214 ,  G06F18/217 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. One of the methods includes obtaining a training data set for training a machine learning model, the training data set comprising a plurality of training inputs; determining a plurality of data augmentation policies, wherein each data augmentation policy defines a procedure for processing a training input to generate a transformed training input; for each data augmentation policy, training the machine learning model using the data augmentation policy; determining, for each data augmentation policy, a quality measure of the machine learning model that has been trained using the data augmentation policy; and selecting a final data augmentation policy based using the quality measures of the machine learning models.

公开(公告)号：US20210019658A1

公开(公告)日：2021-01-21

申请号：US17061103

申请日：2020-10-01

Applicant: Google LLC

Inventor： Vijay Vasudevan ,  Barret Zoph ,  Ekin Dogus Cubuk ,  Quoc V. Le

IPC: G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning a data augmentation policy for training a machine learning model. In one aspect, a method includes: receiving training data for training a machine learning model to perform a particular machine learning task; determining multiple data augmentation policies, comprising, at each of multiple time steps: generating a current data augmentation policy based on quality measures of data augmentation policies generated at previous time steps; training a machine learning model on the training data using the current data augmentation policy; and determining a quality measure of the current data augmentation policy using the machine learning model after it has been trained using the current data augmentation policy; and selecting a final data augmentation policy based on the quality measures of the determined data augmentation policies.

公开(公告)号：US12033038B2

公开(公告)日：2024-07-09

申请号：US17061103

申请日：2020-10-01

Applicant: Google LLC

Inventor： Vijay Vasudevan ,  Barret Zoph ,  Ekin Dogus Cubuk ,  Quoc V. Le

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning a data augmentation policy for training a machine learning model. In one aspect, a method includes: receiving training data for training a machine learning model to perform a particular machine learning task; determining multiple data augmentation policies, comprising, at each of multiple time steps: generating a current data augmentation policy based on quality measures of data augmentation policies generated at previous time steps; training a machine learning model on the training data using the current data augmentation policy; and determining a quality measure of the current data augmentation policy using the machine learning model after it has been trained using the current data augmentation policy; and selecting a final data augmentation policy based on the quality measures of the determined data augmentation policies.

公开(公告)号：US20220253704A1

公开(公告)日：2022-08-11

申请号：US17665457

申请日：2022-02-04

Applicant: Google LLC

Inventor： Ekin Dogus Cubuk ,  Luke Shekerjian Metz ,  Samuel Stern Schoenholz ,  Amil A. Merchant

IPC: G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing optimization using an optimizer neural network. One of the methods includes for each optimizer network parameter, randomly sampling a perturbation value; generating a plurality of sets of candidate values for the optimizer network parameters, for each set of candidate values of the optimizer network parameters: determining a respective loss value representing a performance of the optimizer neural network in updating one or more sets of inner parameters in accordance with the set of candidate of values of the optimizer network parameters; and updating the current values of the optimizer network parameters based on the loss values for the plurality of sets of candidate values of the optimizer network parameters.

公开(公告)号：US20220012537A1

公开(公告)日：2022-01-13

申请号：US17487548

申请日：2021-09-28

Applicant: Google LLC

Inventor： Daniel Sung-Joon Park ,  Quoc V. Le ,  William Chan ,  Ekin Dogus Cubuk ,  Barret Zoph ,  Yu Zhang ,  Chung-Cheng Chiu

IPC: G06K9/62 ,  G10L15/16 ,  G10L15/28 ,  G10L15/06 ,  G10L15/12 ,  G06N20/00

Abstract: Generally, the present disclosure is directed to systems and methods that generate augmented training data for machine-learned models via application of one or more augmentation techniques to audiographic images that visually represent audio signals. In particular, the present disclosure provides a number of novel augmentation operations which can be performed directly upon the audiographic image (e.g., as opposed to the raw audio data) to generate augmented training data that results in improved model performance. As an example, the audiographic images can be or include one or more spectrograms or filter bank sequences.

公开(公告)号：US11205099B2

公开(公告)日：2021-12-21

申请号：US16833449

申请日：2020-03-27

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Quoc V. Le ,  Ekin Dogus Cubuk ,  Barret Zoph

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. One of the methods includes obtaining a training data set for training a machine learning model, the training data set comprising a plurality of training inputs; determining a plurality of data augmentation policies, wherein each data augmentation policy defines a procedure for processing a training input to generate a transformed training input; for each data augmentation policy, training the machine learning model using the data augmentation policy; determining, for each data augmentation policy, a quality measure of the machine learning model that has been trained using the data augmentation policy; and selecting a final data augmentation policy based using the quality measures of the machine learning models.

公开(公告)号：US12293266B2

公开(公告)日：2025-05-06

申请号：US18584625

申请日：2024-02-22

Applicant: Google LLC

Inventor： Vijay Vasudevan ,  Barret Zoph ,  Ekin Dogus Cubuk ,  Quoc V. Le

IPC: G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning a data augmentation policy for training a machine learning model. In one aspect, a method includes: receiving training data for training a machine learning model to perform a particular machine learning task; determining multiple data augmentation policies, comprising, at each of multiple time steps: generating a current data augmentation policy based on quality measures of data augmentation policies generated at previous time steps; training a machine learning model on the training data using the current data augmentation policy; and determining a quality measure of the current data augmentation policy using the machine learning model after it has been trained using the current data augmentation policy; and selecting a final data augmentation policy based on the quality measures of the determined data augmentation policies.

公开(公告)号：US20230274532A1

公开(公告)日：2023-08-31

申请号：US18313772

申请日：2023-05-08

Applicant: Google LLC

Inventor： Jon Shlens ,  Ekin Dogus Cubuk ,  Quoc Le ,  Tsung-Yi Lin ,  Barret Zoph ,  Golnaz Ghiasi

IPC: G06V10/772 ,  G06T3/60 ,  G06T3/20 ,  G06T11/00 ,  G06F18/24 ,  G06F18/21

CPC classification number: G06V10/772 ,  G06F18/217 ,  G06F18/24 ,  G06T3/20 ,  G06T3/60 ,  G06T11/001

Abstract: Example aspects of the present disclosure are directed to systems and methods for learning data augmentation strategies for improved object detection model performance. In particular, example aspects of the present disclosure are directed to iterative reinforcement learning approaches in which, at each of a plurality of iterations, a controller model selects a series of one or more augmentation operations to be applied to training images to generate augmented images. For example, the controller model can select the augmentation operations from a defined search space of available operations which can, for example, include operations that augment the training image without modification of the locations of a target object and corresponding bounding shape within the image and/or operations that do modify the locations of the target object and bounding shape within the training image.

公开(公告)号：US20220215682A1

公开(公告)日：2022-07-07

申请号：US17702438

申请日：2022-03-23

Applicant: Google LLC

Inventor： Jon Shlens ,  Ekin Dogus Cubuk ,  Quoc Le ,  Tsung-Yi Lin ,  Barret Zoph ,  Golnaz Ghiasi

IPC: G06V30/194 ,  G06K9/62 ,  G06T3/60 ,  G06T3/20 ,  G06T11/00

Abstract: Example aspects of the present disclosure are directed to systems and methods for learning data augmentation strategies for improved object detection model performance. In particular, example aspects of the present disclosure are directed to iterative reinforcement learning approaches in which, at each of a plurality of iterations, a controller model selects a series of one or more augmentation operations to be applied to training images to generate augmented images. For example, the controller model can select the augmentation operations from a defined search space of available operations which can, for example, include operations that augment the training image without modification of the locations of a target object and corresponding bounding shape within the image and/or operations that do modify the locations of the target object and bounding shape within the training image.