知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.016 seconds)

    Domain Adaptation for Machine Learning Models
    1.
    发明申请
    Domain Adaptation for Machine Learning Models 有权

    公开(公告)号：US20210334664A1

    公开(公告)日：2021-10-28

    申请号：US16865605

    申请日：2020-05-04

    Applicant: Adobe Inc.

    Inventor： Kai Li ,  Christopher Alan Tensmeyer ,  Curtis Michael Wigington ,  Handong Zhao ,  Nikolaos Barmpalios ,  Tong Sun ,  Varun Manjunatha ,  Vlad Ion Morariu

    IPC: G06N3/08 ,  G06N20/10 ,  G06K9/62 ,  G06K9/00 ,  G06F17/18

    Abstract: Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.

    DOMAIN ALIGNMENT FOR OBJECT DETECTION DOMAIN ADAPTATION TASKS
    4.
    发明申请
    DOMAIN ALIGNMENT FOR OBJECT DETECTION DOMAIN ADAPTATION TASKS 有权

    公开(公告)号：US20210312232A1

    公开(公告)日：2021-10-07

    申请号：US16885168

    申请日：2020-05-27

    Applicant: Adobe Inc.

    Inventor： Christopher Tensmeyer ,  Vlad Ion Morariu ,  Varun Manjunatha ,  Tong Sun ,  Nikolaos Barmpalios ,  Kai Li ,  Handong Zhao ,  Curtis Wigington

    IPC: G06K9/62 ,  G06N5/04 ,  G06K9/00

    Abstract: A domain alignment technique for cross-domain object detection tasks is introduced. During a preliminary pretraining phase, an object detection model is pretrained to detect objects in images associated with a source domain using a source dataset of images associated with the source domain. After completing the pretraining phase, a domain adaptation phase is performed using the source dataset and a target dataset to adapt the pretrained object detection model to detect objects in images associated with the target domain. The domain adaptation phase may involve the use of various domain alignment modules that, for example, perform multi-scale pixel/path alignment based on input feature maps or perform instance-level alignment based on input region proposals.

    Domain Adaptation for Machine Learning Models
    6.
    发明申请
    Domain Adaptation for Machine Learning Models 有权

    公开(公告)号：US20220391768A1

    公开(公告)日：2022-12-08

    申请号：US17883811

    申请日：2022-08-09

    Applicant: Adobe Inc.

    Inventor： Kai Li ,  Christopher Alan Tensmeyer ,  Curtis Michael Wigington ,  Handong Zhao ,  Nikolaos Barmpalios ,  Tong Sun ,  Varun Manjunatha ,  Vlad Ion Morariu

    IPC: G06N20/00 ,  G06N3/04

    Abstract: Adapting a machine learning model to process data that differs from training data used to configure the model for a specified objective is described. A domain adaptation system trains the model to process new domain data that differs from a training data domain by using the model to generate a feature representation for the new domain data, which describes different content types included in the new domain data. The domain adaptation system then generates a probability distribution for each discrete region of the new domain data, which describes a likelihood of the region including different content described by the feature representation. The probability distribution is compared to ground truth information for the new domain data to determine a loss function, which is used to refine model parameters. After determining that model outputs achieve a threshold similarity to the ground truth information, the model is output as a domain-agnostic model.

Patent Agency Ranking