公开(公告)号：US11907850B2

公开(公告)日：2024-02-20

申请号：US17454516

申请日：2021-11-11

Applicant: Google LLC

Inventor： Rui Zhang ,  Jia Li ,  Tomas Jon Pfister

IPC: G06N3/084 ,  G06F18/214 ,  G06F18/22 ,  G06F18/21 ,  G06F18/2413 ,  G06F18/2134 ,  G06N3/045 ,  G06N3/047 ,  G06V10/74 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06N3/084 ,  G06F18/214 ,  G06F18/2148 ,  G06F18/2193 ,  G06F18/21347 ,  G06F18/22 ,  G06F18/2413 ,  G06N3/045 ,  G06N3/047 ,  G06V10/761 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82

Abstract: A method includes obtaining a source training dataset that includes a plurality of source training images and obtaining a target training dataset that includes a plurality of target training images. For each source training image, the method includes translating, using the forward generator neural network G, the source training image to a respective translated target image according to current values of forward generator parameters. For each target training image, the method includes translating, using a backward generator neural network F, the target training image to a respective translated source image according to current values of backward generator parameters. The method also includes training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function.

公开(公告)号：US20220067441A1

公开(公告)日：2022-03-03

申请号：US17454516

申请日：2021-11-11

Applicant: Google LLC

Inventor： Rui Zhang ,  Jia Li ,  Tomas Jon Pfister

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: A method includes obtaining a source training dataset that includes a plurality of source training images and obtaining a target training dataset that includes a plurality of target training images. For each source training image, the method includes translating, using the forward generator neural network G, the source training image to a respective translated target image according to current values of forward generator parameters. For each target training image, the method includes translating, using a backward generator neural network F, the target training image to a respective translated source image according to current values of backward generator parameters. The method also includes training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function.

公开(公告)号：US20240160937A1

公开(公告)日：2024-05-16

申请号：US18418197

申请日：2024-01-19

Applicant: Google LLC

Inventor： Rui Zhang ,  Jia Li ,  Tomas Jon Pfister

IPC: G06N3/084 ,  G06F18/21 ,  G06F18/2134 ,  G06F18/214 ,  G06F18/22 ,  G06F18/2413 ,  G06N3/045 ,  G06N3/047 ,  G06V10/74 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06N3/084 ,  G06F18/21347 ,  G06F18/214 ,  G06F18/2148 ,  G06F18/2193 ,  G06F18/22 ,  G06F18/2413 ,  G06N3/045 ,  G06N3/047 ,  G06V10/761 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82

Abstract: A method includes obtaining a source training dataset that includes a plurality of source training images and obtaining a target training dataset that includes a plurality of target training images. For each source training image, the method includes translating, using the forward generator neural network G, the source training image to a respective translated target image according to current values of forward generator parameters. For each target training image, the method includes translating, using a backward generator neural network F, the target training image to a respective translated source image according to current values of backward generator parameters. The method also includes training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function.

公开(公告)号：US11205096B2

公开(公告)日：2021-12-21

申请号：US16688773

申请日：2019-11-19

Applicant: Google LLC

Inventor： Rui Zhang ,  Jia Li ,  Tomas Jon Pfister

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: A computer-implemented method for training a forward generator neural network G to translate a source image in a source domain X to a corresponding target image in a target domain Y is described. The method includes: obtaining a source training dataset sampled from the source domain X according to a source domain distribution, the source training dataset comprising a plurality of source training images; obtaining a target training dataset sampled from the target domain Y according to a target domain distribution, the target training dataset comprising a plurality of target training images; for each of the source training images in the source training dataset, translating, using the forward generator neural network G, each source training image to a respective translated target image in the target domain Y according to current values of forward generator parameters of the forward generator neural network G; for each of the target training images in the target training dataset, translating, using a backward generator neural network F, each target training image to a respective translated source image in the source domain X according to current values of backward generator parameters of the backward generator neural network F; and training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function, wherein the objective function comprises a harmonic loss component that ensures (i) similarity-consistency between patches in each source training image and patches in its corresponding translated target image, and (ii) similarity-consistency between patches in each target training image and patches in its corresponding translated source image.

公开(公告)号：US20200160113A1

公开(公告)日：2020-05-21

申请号：US16688773

申请日：2019-11-19

Applicant: Google LLC

Inventor： Rui Zhang ,  Jia Li ,  Tomas Jon Pfister

IPC: G06K9/62 ,  G06N3/04

Abstract: A computer-implemented method for training a forward generator neural network G to translate a source image in a source domain X to a corresponding target image in a target domain Y is described. The method includes: obtaining a source training dataset sampled from the source domain X according to a source domain distribution, the source training dataset comprising a plurality of source training images; obtaining a target training dataset sampled from the target domain Y according to a target domain distribution, the target training dataset comprising a plurality of target training images; for each of the source training images in the source training dataset, translating, using the forward generator neural network G, each source training image to a respective translated target image in the target domain Y according to current values of forward generator parameters of the forward generator neural network G; for each of the target training images in the target training dataset, translating, using a backward generator neural network F, each target training image to a respective translated source image in the source domain X according to current values of backward generator parameters of the backward generator neural network F; and training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function, wherein the objective function comprises a harmonic loss component that ensures (i) similarity-consistency between patches in each source training image and patches in its corresponding translated target image, and (ii) similarity-consistency between patches in each target training image and patches in its corresponding translated source image.