中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.014 seconds)

    MULTI-EXPERT ADVERSARIAL REGULARIZATION FOR ROBUST AND DATA-EFFICIENT DEEP SUPERVISED LEARNING
    4.
    发明申请
    MULTI-EXPERT ADVERSARIAL REGULARIZATION FOR ROBUST AND DATA-EFFICIENT DEEP SUPERVISED LEARNING 有权

    公开(公告)号：US20220301296A1

    公开(公告)日：2022-09-22

    申请号：US17674832

    申请日：2022-02-17

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Behnam BABAGHOLAMI MOHAMADABADI ,  Qingfeng LIU ,  Mostafa EL-KHAMY ,  Jungwon LEE

    IPC: G06V10/82 ,  G06N5/04 ,  G06V10/778 ,  G06V10/776 ,  G06V10/774

    Abstract: A system and a method to train a neural network are disclosed. A first image is weakly and strongly augmented. The first image, the weakly and strongly augmented first images are input into a feature extractor to obtain augmented features. Each weakly augmented first image is input to a corresponding first expert head to determine a supervised loss for each weakly augmented first image. Each strongly augmented first image is input to a corresponding second expert head to determine a diversity loss for each strongly augmented first image. The feature extractor is trained to minimize the supervised loss on weakly augmented first images and to minimize a multi-expert consensus loss on strongly augmented first images. Each first expert head is trained to minimize the supervised loss for each weakly augmented first image, and each second expert head is trained to minimize the diversity loss for each strongly augmented first image.

    TEMPORAL CONSISTENCY VIA BACKBONE FEATURE FUSION FOR PIXEL-LEVEL PREDICTION TASKS
    5.
    发明申请
    TEMPORAL CONSISTENCY VIA BACKBONE FEATURE FUSION FOR PIXEL-LEVEL PREDICTION TASKS 有权

    公开(公告)号：US20250069247A1

    公开(公告)日：2025-02-27

    申请号：US18943520

    申请日：2024-11-11

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Haoyu REN ,  Mostafa EL-KHAMY ,  Jungwon LEE ,  Hai SU ,  Qingfeng LIU

    IPC: G06T7/579 ,  G06T3/18 ,  G06T7/194

    Abstract: Methods and systems for performing video prediction, including obtaining an input frame from among a plurality of frames included in an input video; extracting a first feature map by providing the input frame to a first plurality of feature extraction layers and a first strided convolutional layer included in an encoder; providing the first feature map and at least one neighboring first feature map corresponding to at least one neighboring frame to a first fusion module included in the encoder; fusing the first feature map with the at least one neighboring first feature map to generate a fused first feature map using the first fusion module; generating a prediction corresponding to the input frame based on the fused first feature map using a decoder; and performing a video prediction task using the prediction.

    METHOD AND DEVICE FOR DEEP GUIDED FILTER PROCESSING
    6.
    发明申请
    METHOD AND DEVICE FOR DEEP GUIDED FILTER PROCESSING 有权

    公开(公告)号：US20220301128A1

    公开(公告)日：2022-09-22

    申请号：US17563012

    申请日：2021-12-27

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Qingfeng LIU ,  Hai SU ,  Mostafa EL-KHAMY

    IPC: G06T5/20 ,  G06V10/44 ,  G06T7/12 ,  G06T3/40 ,  G06V20/70

    Abstract: A method of image processing includes: determining a first feature, wherein the first feature has a dimensionality D1; determining a second feature, wherein the second feature has a dimensionality D2 and is based on an output of a feature extraction network; generating a third feature by processing the first feature, the third feature having a dimensionality D3; generating a guidance by processing the second feature, the guidance having the dimensionality D3; generating a filter output by applying a deep guided filter (DGF) to the third feature using the guidance; generating a map based on the filter output; and outputting a processed image based on the map.

Patent Agency Ranking