中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

20 records (took 0.014 seconds)

    IMAGE MANIPULATION BY TEXT INSTRUCTION
    11.
    发明公开
    IMAGE MANIPULATION BY TEXT INSTRUCTION 审中-公开

    公开(公告)号：US20230177754A1

    公开(公告)日：2023-06-08

    申请号：US18085487

    申请日：2022-12-20

    Applicant: Google LLC

    Inventor： Tianhao Zhang ,  Weilong Yang ,  Honglak Lee ,  Hung-Yu Tseng ,  Irfan Aziz Essa ,  Lu Jiang

    IPC: G06T11/60 ,  G06T3/00 ,  G06N3/088 ,  G06T3/40 ,  G06T9/00 ,  G06N3/045

    CPC classification number: G06T11/60 ,  G06T3/0006 ,  G06N3/088 ,  G06T3/40 ,  G06T9/002 ,  G06N3/045

    Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

    Image manipulation by text instruction
    12.
    发明授权
    Image manipulation by text instruction 有权

    公开(公告)号：US11562518B2

    公开(公告)日：2023-01-24

    申请号：US17340671

    申请日：2021-06-07

    Applicant: Google LLC

    Inventor： Tianhao Zhang ,  Weilong Yang ,  Honglak Lee ,  Hung-Yu Tseng ,  Irfan Aziz Essa ,  Lu Jiang

    IPC: G06T11/60 ,  G06T3/00 ,  G06N3/04 ,  G06N3/08 ,  G06T3/40 ,  G06T9/00

    Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

    REINFORCEMENT LEARNING ALGORITHM SEARCH
    13.
    发明申请
    REINFORCEMENT LEARNING ALGORITHM SEARCH 有权

    公开(公告)号：US20220391687A1

    公开(公告)日：2022-12-08

    申请号：US17338093

    申请日：2021-06-03

    Applicant: Google LLC

    Inventor： John Dalton Co-Reyes ,  Yingjie Miao ,  Daiyi Peng ,  Sergey Vladimir Levine ,  Quoc V. Le ,  Honglak Lee ,  Aleksandra Faust

    IPC: G06N3/08 ,  G06F11/34 ,  G06F16/901

    Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for generating and searching reinforcement learning algorithms. In some implementations, a computer-implemented system generates a sequence of candidate reinforcement learning algorithms. Each candidate reinforcement learning algorithm in the sequence is configured to receive an input environment state characterizing a state of an environment and to generate an output that specifies an action to be performed by an agent interacting with the environment. For each candidate reinforcement learning algorithm in the sequence, the system performs a performance evaluation for a set of a plurality of training environments. For each training environment, the system adjusts a set of environment-specific parameters of the candidate reinforcement learning algorithm by performing training of the candidate reinforcement learning algorithm to control a corresponding agent in the training environment. The system generates an environment-specific performance metric for the candidate reinforcement learning algorithm that measures a performance of the candidate reinforcement learning algorithm in controlling the corresponding agent in the training environment as a result of the training. After performing training in the set of training environments, the system generates a summary performance metric for the candidate reinforcement learning algorithm by combining the environment-specific performance metrics generated for the set of training environments. After evaluating each of the candidate reinforcement learning algorithms in the sequence, the system selects one or more output reinforcement learning algorithms from the sequence based on the summary performance metrics of the candidate reinforcement learning algorithms.

    IMAGE MANIPULATION BY TEXT INSTRUCTION
    14.
    发明申请
    IMAGE MANIPULATION BY TEXT INSTRUCTION 有权

    公开(公告)号：US20210383584A1

    公开(公告)日：2021-12-09

    申请号：US17340671

    申请日：2021-06-07

    Applicant: Google LLC

    Inventor： Tianhao Zhang ,  Weilong Yang ,  Honglak Lee ,  Hung-Yu Tseng ,  Irfan Aziz Essa ,  Lu Jiang

    IPC: G06T11/60 ,  G06T3/00 ,  G06T3/40 ,  G06N3/08 ,  G06N3/04

    Abstract: A method for generating an output image from an input image and an input text instruction that specifies a location and a modification of an edit applied to the input image using a neural network is described. The neural network includes an image encoder, an image decoder, and an instruction attention network. The method includes receiving the input image and the input text instruction; extracting, from the input image, an input image feature that represents features of the input image using the image encoder; generating a spatial feature and a modification feature from the input text instruction using the instruction attention network; generating an edited image feature from the input image feature, the spatial feature and the modification feature; and generating the output image from the edited image feature using the image decoder.

    Data-efficient hierarchical reinforcement learning
    18.
    发明授权
    Data-efficient hierarchical reinforcement learning 有权

    公开(公告)号：US11992944B2

    公开(公告)日：2024-05-28

    申请号：US17050546

    申请日：2019-05-17

    Applicant: Google LLC

    Inventor： Honglak Lee ,  Shixiang Gu ,  Sergey Levine

    IPC: B25J9/16

    CPC classification number: B25J9/163

    Abstract: Training and/or utilizing a hierarchical reinforcement learning (HRL) model for robotic control. The HRL model can include at least a higher-level policy model and a lower-level policy model. Some implementations relate to technique(s) that enable more efficient off-policy training to be utilized in training of the higher-level policy model and/or the lower-level policy model. Some of those implementations utilize off-policy correction, which re-labels higher-level actions of experience data, generated in the past utilizing a previously trained version of the HRL model, with modified higher-level actions. The modified higher-level actions are then utilized to off-policy train the higher-level policy model. This can enable effective off-policy training despite the lower-level policy model being a different version at training time (relative to the version when the experience data was collected).

    Systems And Methods For Generating Predicted Visual Observations Of An Environment Using Machine Learned Models
    19.
    发明申请
    Systems And Methods For Generating Predicted Visual Observations Of An Environment Using Machine Learned Models 有权

    公开(公告)号：US20230072293A1

    公开(公告)日：2023-03-09

    申请号：US17409249

    申请日：2021-08-23

    Applicant: Google LLC

    Inventor： Jing Yu Koh ,  Honglak Lee ,  Yinfei Yang ,  Jason Michael Baldridge ,  Peter James Anderson

    IPC: G06T11/00 ,  G06T15/00 ,  G06T15/08 ,  G06K9/62 ,  G06T7/10 ,  G06N3/08 ,  G06N3/04

    Abstract: A computing system for generating predicted images along a trajectory of unseen viewpoints. The system can obtain one or more spatial observations of an environment that may be captured from one or more previous camera poses. The system can generate a three-dimensional point cloud for the environment from the one or more spatial observations and the one or more previous camera poses. The system can project the three-dimensional point cloud into two-dimensional space to form one or more guidance spatial observations. The system can process the one or more guidance spatial observations with a machine-learned spatial observation prediction model to generate one or more predicted spatial observations. The system can process the one or more predicted spatial observations and image data with a machine-learned image prediction model to generate one or more predicted images from the target camera pose. The system can output the one or more predicted images.

    DATA-EFFICIENT HIERARCHICAL REINFORCEMENT LEARNING
    20.
    发明申请
    DATA-EFFICIENT HIERARCHICAL REINFORCEMENT LEARNING 有权

    公开(公告)号：US20210187733A1

    公开(公告)日：2021-06-24

    申请号：US17050546

    申请日：2019-05-17

    Applicant: Google LLC

    Inventor： Honglak Lee ,  Shixiang Gu ,  Sergey Levine

    IPC: B25J9/16

    Abstract: Training and/or utilizing a hierarchical reinforcement learning (HRL) model for robotic control. The HRL model can include at least a higher-level policy model and a lower-level policy model. Some implementations relate to technique(s) that enable more efficient off-policy training to be utilized in training of the higher-level policy model and/or the lower-level policy model. Some of those implementations utilize off-policy correction, which re-labels higher-level actions of experience data, generated in the past utilizing a previously trained version of the HRL model, with modified higher-level actions. The modified higher-level actions are then utilized to off-policy train the higher-level policy model. This can enable effective off-policy training despite the lower-level policy model being a different version at training time (relative to the version when the experience data was collected).

Patent Agency Ranking