知搜-全球专利检索

  1. 登录
  2. 注册

搜索结果

160 条记录 (耗时 0.019 秒)

    METHOD AND DEVICE FOR ON-VEHICLE ACTIVE LEARNING TO BE USED FOR TRAINING PERCEPTION NETWORK OF AUTONOMOUS VEHICLE
    2.
    发明申请
    METHOD AND DEVICE FOR ON-VEHICLE ACTIVE LEARNING TO BE USED FOR TRAINING PERCEPTION NETWORK OF AUTONOMOUS VEHICLE 有权

    公开(公告)号：US20210334652A1

    公开(公告)日：2021-10-28

    申请号：US17204287

    申请日：2021-03-17

    申请人： Stradvision, Inc.

    发明人： Hongmo Je ,  Bongnam Kang ,  Yongjoong Kim ,  Sung An Gweon

    IPC分类号： G06N3/08 ,  G06N3/04

    摘要： A method of on-vehicle active learning for training a perception network of an autonomous vehicle is provided. The method includes steps of: an on-vehicle active learning device, (a) if a driving video and sensing information are acquired from a camera and sensors on an autonomous vehicle, inputting frames of the driving video and the sensing information into a scene code assigning module to generate scene codes including information on scenes in the frames and on driving events; and (b) at least one of selecting a part of the frames, whose object detection information satisfies a condition, as specific frames by using the scene codes and the object detection information and selecting a part of the frames, matching a training policy, as the specific frames by using the scene codes and the object detection information, and storing the specific frames and specific scene codes in a frame storing part.

    Learning method and learning device for training an object detection network by using attention maps and testing method and testing device using the same
    4.
    发明授权
    Learning method and learning device for training an object detection network by using attention maps and testing method and testing device using the same 有权

    公开(公告)号：US10970598B1

    公开(公告)日：2021-04-06

    申请号：US17112413

    申请日：2020-12-04

    申请人： Stradvision, Inc.

    发明人： Wooju Ryu ,  Hongmo Je ,  Bongnam Kang ,  Yongjoong Kim

    IPC分类号： G06K9/62 ,  G06N3/08 ,  G06K9/32 ,  G06N3/04 ,  G06K9/00

    摘要： A method for training an object detection network by using attention maps is provided. The method includes steps of: (a) an on-device learning device inputting the training images into a feature extraction network, inputting outputs of the feature extraction network into a attention network and a concatenation layer, and inputting outputs of the attention network into the concatenation layer; (b) the on-device learning device inputting outputs of the concatenation layer into an RPN and an ROI pooling layer, inputting outputs of the RPN into a binary convertor and the ROI pooling layer, and inputting outputs of the ROI pooling layer into a detection network and thus to output object detection data; and (c) the on-device learning device train at least one of the feature extraction network, the detection network, the RPN and the attention network through backpropagations using an object detection losses, an RPN losses, and a cross-entropy losses.

    Method for training deep learning network based on artificial intelligence and learning device using the same
    5.
    发明授权
    Method for training deep learning network based on artificial intelligence and learning device using the same 有权

    公开(公告)号：US10963792B1

    公开(公告)日：2021-03-30

    申请号：US17111539

    申请日：2020-12-04

    申请人： Stradvision, Inc.

    发明人： Kye-Hyeon Kim ,  Hongmo Je ,  Bongnam Kang ,  Wooju Ryu

    IPC分类号： G06N3/00 ,  G06N3/08 ,  G06K9/62

    摘要： A method for training a deep learning network based on artificial intelligence is provided. The method includes steps of: a learning device (a) inputting unlabeled data into an active learning network to acquire sub unlabeled data and inputting the sub unlabeled data into an auto labeling network to generate new labeled data; (b) allowing a continual learning network to sample the new labeled data and existing labeled data to generate a mini-batch, and train the existing learning network using the mini-batch to acquire a trained learning network, wherein part of the mini-batch are selected by referring to specific existing losses; and (c) (i) allowing an explainable analysis network to generate insightful results on validation data and transmit the insightful results to a human engineer to transmit an analysis of the trained learning network and (ii) modifying at least one of the active learning network and the continual learning network.