-
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
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
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：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.
-
Patent Agency Ranking
公开(公告)号：US11087201B2
公开(公告)日：2021-08-10
申请号：US16861491
申请日：2020-04-29
Applicant: Google LLC
Inventor： Wei Hua , Barret Zoph , Jonathon Shlens , Chenxi Liu , Jonathan Huang , Jia Li , Fei-Fei Li , Kevin Patrick Murphy
Abstract: A method for determining an architecture for a task neural network configured to perform a particular machine learning task is described. The method includes obtaining data specifying a current set of candidate architectures for the task neural network; for each candidate architecture in the current set: processing the data specifying the candidate architecture using a performance prediction neural network having multiple performance prediction parameters, the performance prediction neural network being configured to process the data specifying the candidate architecture in accordance with current values of the performance prediction parameters to generate a performance prediction that characterizes how well a neural network having the candidate architecture would perform after being trained on the particular machine learning task; and generating an updated set of candidate architectures by selecting one or more of the candidate architectures in the current set based on the performance predictions for the candidate architectures in the current set.
-
公开(公告)号：US20210334624A1
公开(公告)日：2021-10-28
申请号：US17365939
申请日：2021-07-01
Applicant: Google LLC
Inventor： Wei Hua , Barret Zoph , Jonathon Shlens , Chenxi Liu , Jonathan Huang , Jia Li , Fei-Fei Li , Kevin Patrick Murphy
Abstract: A method for determining an architecture for a task neural network configured to perform a particular machine learning task is described. The method includes obtaining data specifying a current set of candidate architectures for the task neural network; for each candidate architecture in the current set: processing the data specifying the candidate architecture using a performance prediction neural network having multiple performance prediction parameters, the performance prediction neural network being configured to process the data specifying the candidate architecture in accordance with current values of the performance prediction parameters to generate a performance prediction that characterizes how well a neural network having the candidate architecture would perform after being trained on the particular machine learning task; and generating an updated set of candidate architectures by selecting one or more of the candidate architectures in the current set based on the performance predictions for the candidate architectures in the current set.
-
公开(公告)号：US20200257961A1
公开(公告)日：2020-08-13
申请号：US16861491
申请日：2020-04-29
Applicant: Google LLC
Inventor： Wei Hua , Barret Zoph , Jonathon Shlens , Chenxi Liu , Jonathan Huang , Jia Li , Fei-Fei Li , Kevin Patrick Murphy
Abstract: A method for determining an architecture for a task neural network configured to perform a particular machine learning task is described. The method includes obtaining data specifying a current set of candidate architectures for the task neural network; for each candidate architecture in the current set: processing the data specifying the candidate architecture using a performance prediction neural network having multiple performance prediction parameters, the performance prediction neural network being configured to process the data specifying the candidate architecture in accordance with current values of the performance prediction parameters to generate a performance prediction that characterizes how well a neural network having the candidate architecture would perform after being trained on the particular machine learning task; and generating an updated set of candidate architectures by selecting one or more of the candidate architectures in the current set based on the performance predictions for the candidate architectures in the current set.
-
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
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.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.012 seconds)
