中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

82 records (took 0.025 seconds)

    METHOD AND APPARATUS FOR GENERATING DEPTH IMAGE
    1.
    发明申请
    METHOD AND APPARATUS FOR GENERATING DEPTH IMAGE 有权

    公开(公告)号：US20250069246A1

    公开(公告)日：2025-02-27

    申请号：US18944857

    申请日：2024-11-12

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Jihye KIM ,  Seon Min RHEE ,  Heewon KIM ,  Seungju HAN ,  Jaejoon HAN

    IPC: G06T7/55

    Abstract: A method and apparatus for generating a depth image are provided. The apparatus receives an input image, extracts a feature corresponding to the input image, generates features for each depth resolution by decoding the feature using decoders corresponding to different depth resolutions, estimates probability distributions for each depth resolution by progressively refining the features for each depth resolution, and generates a target depth image corresponding to the input image based on a final estimated probability distribution from among the probability distributions for each depth resolution.

    METHOD AND DEVICE WITH OBJECT CLASSIFICATION
    2.
    发明公开
    METHOD AND DEVICE WITH OBJECT CLASSIFICATION 审中-公开

    公开(公告)号：US20240161458A1

    公开(公告)日：2024-05-16

    申请号：US18193712

    申请日：2023-03-31

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Kikyung KIM ,  Jiwon BAEK ,  Chanho AHN ,  Seungju HAN

    IPC: G06V10/764 ,  G06V10/70

    CPC classification number: G06V10/764 ,  G06V10/87

    Abstract: Disclosed is a method that includes generating a prediction consistency value that indicates a consistency of prediction of an object in an input image with respect to class prediction values for the object in an input image from classification models to which the input image is input, and identifying a class of the object. Identifying the class of the object includes, in response to a class type being determined, based on the prediction consistency value, of the object being determined to correspond to a majority class, identifying a class of the object based on a corresponding class prediction value output for the object from a majority class prediction model, and in response to the class type of the object being determined to correspond to a minority class, identifying the class of the object based on another corresponding class prediction value output for the object from a minority class prediction model.

    METHOD AND DEVICE WITH ENSEMBLE MODEL FOR DATA LABELING
    4.
    发明公开
    METHOD AND DEVICE WITH ENSEMBLE MODEL FOR DATA LABELING 审中-公开

    公开(公告)号：US20240143976A1

    公开(公告)日：2024-05-02

    申请号：US18193781

    申请日：2023-03-31

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Huijin LEE ,  Wissam BADDAR ,  Saehyun AHN ,  Seungju HAN

    IPC: G06N3/045

    CPC classification number: G06N3/045

    Abstract: A method and device for labeling are provided. A labeling method includes: determining inference performance features of respective neural network models included in an ensemble model, wherein the inference performance features correspond to performance of the neural network models with respect to inferring classes of the ensemble model; based on the inference performance features, determining weights for each of the classes for each of the neural network models, wherein the weights are not weights of nodes of the neural network models; generating classification result data by performing a classification inference operation on labeling target inputs by the neural network models; determining score data representing confidences for each of the classes for the labeling target inputs by applying weights of the weight data to the classification result data; and measuring classification accuracy of the classification operation for the labeling target inputs based on the score data.

Patent Agency Ranking