中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.009 seconds)

    LEARNING METHOD AND LEARNING DEVICE FOR UPDATING OBJECT DETECTOR, BASED ON DEEP LEARNING, OF AUTONOMOUS VEHICLE TO ADAPT THE OBJECT DETECTOR TO DRIVING CIRCUMSTANCE, AND UPDATING METHOD AND UPDATING DEVICE USING THE SAME
    1.
    发明申请
    LEARNING METHOD AND LEARNING DEVICE FOR UPDATING OBJECT DETECTOR, BASED ON DEEP LEARNING, OF AUTONOMOUS VEHICLE TO ADAPT THE OBJECT DETECTOR TO DRIVING CIRCUMSTANCE, AND UPDATING METHOD AND UPDATING DEVICE USING THE SAME 审中-公开

    公开(公告)号：WO2021230574A1

    公开(公告)日：2021-11-18

    申请号：PCT/KR2021/005723

    申请日：2021-05-07

    Applicant: STRADVISION, INC.

    Inventor： RYU, Wooju ,  JE, Hongmo ,  KANG, Bongnam ,  KIM, Yongjoong

    IPC: G06N3/08 ,  G06N3/04 ,  B60W60/00 ,  G05D1/00

    Abstract: A method for updating an object detector of an autonomous vehicle to adapt the object detector to a driving circumstance is provided. The method includes steps of: a learning device (a) (i) inputting a training image, corresponding to a driving circumstance, into a circumstance-specific object detector to apply (i-1) convolution to the training image to generate a circumstance-specific feature map, (i-2) ROI pooling to the circumstance-specific feature map to generate a circumstance-specific pooled feature map, and (i-3) fully-connected operation to the circumstance-specific pooled feature map to generate circumstance-specific object detection information and (ii) inputting the circumstance-specific feature map into a circumstance-specific ranking network to (ii-1) apply deconvolution to the circumstance-specific feature map and generate a circumstance-specific segmentation map and (ii-2) generate a circumstance-specific rank score via a circumstance-specific discriminator; and (b) training the circumstance-specific object detector, the circumstance-specific deconvolutional layer, the circumstance-specific convolutional layer, and the circumstance-specific discriminator.

    LEARNING METHOD AND LEARNING DEVICE FOR TRAINING AN OBJECT DETECTION NETWORK BY USING ATTENTION MAPS AND TESTING METHOD AND TESTING DEVICE USING THE SAME
    2.
    发明申请
    LEARNING METHOD AND LEARNING DEVICE FOR TRAINING AN OBJECT DETECTION NETWORK BY USING ATTENTION MAPS AND TESTING METHOD AND TESTING DEVICE USING THE SAME 审中-公开

    公开(公告)号：WO2021230457A1

    公开(公告)日：2021-11-18

    申请号：PCT/KR2020/019160

    申请日：2020-12-24

    Applicant: STRADVISION, INC.

    Inventor： RYU, Wooju ,  JE, Hongmo ,  KANG, Bongnam ,  KIM, Yongjoong

    IPC: G06N3/08 ,  G06N3/04 ,  G06N20/00

    Abstract: 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 PERFORMING ADJUSTABLE CONTINUAL LEARNING ON DEEP NEURAL NETWORK MODEL BY USING SELECTIVE DEEP GENERATIVE REPLAY MODULE AND DEVICE USING THE SAME
    3.
    发明申请
    METHOD FOR PERFORMING ADJUSTABLE CONTINUAL LEARNING ON DEEP NEURAL NETWORK MODEL BY USING SELECTIVE DEEP GENERATIVE REPLAY MODULE AND DEVICE USING THE SAME 审中-公开

    公开(公告)号：WO2021235701A1

    公开(公告)日：2021-11-25

    申请号：PCT/KR2021/004696

    申请日：2021-04-14

    Applicant: STRADVISION, INC.

    Inventor： BOO, Suk Hoon ,  GWEON, Sung An ,  KIM, Yongjoong ,  RYU, Wooju

    IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063

    Abstract: A method of adjustable continual learning of a deep neural network model by using a selective deep generative replay module is provided. The method includes steps of: a learning device (a) (i) inputting training data from a total database and a sub-database into the selective deep generative replay module to generate first and second low-dimensional distribution features, (ii) inputting binary values, random parameters, and the second low-dimensional distribution features into a data generator to generate a third training data, and (ii) inputting a first training data into a solver to generate labeled training data; (b) inputting the training data, the low-dimensional distribution features, and the binary values into a discriminator to generate a first and a second training data scores, a first and a second feature distribution scores, and a third training data score; and (c) training the discriminator, the data generator, the distribution analyzer and the solver.

    METHOD FOR TRAINING DEEP LEARNING NETWORK BASED ON ARTIFICIAL INTELLIGENCE AND LEARNING DEVICE USING THE SAME
    4.
    发明申请
    METHOD FOR TRAINING DEEP LEARNING NETWORK BASED ON ARTIFICIAL INTELLIGENCE AND LEARNING DEVICE USING THE SAME 审中-公开

    公开(公告)号：WO2021194056A1

    公开(公告)日：2021-09-30

    申请号：PCT/KR2020/018593

    申请日：2020-12-17

    Applicant: STRADVISION, INC.

    Inventor： KIM, Kye-Hyeon ,  JE, Hongmo ,  KANG, Bongnam ,  RYU, Wooju

    IPC: G06N3/08 ,  G06N3/04 ,  G06K9/6202 ,  G06K9/623 ,  G06K9/6259 ,  G06K9/6262 ,  G06K9/6263 ,  G06K9/6272 ,  G06N3/084

    Abstract: 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.

    METHOD FOR EXPLAINABLE ACTIVE LEARNING, TO BE USED FOR OBJECT DETECTOR, BY USING DEEP ENCODER AND ACTIVE LEARNING DEVICE USING THE SAME
    5.
    发明申请
    METHOD FOR EXPLAINABLE ACTIVE LEARNING, TO BE USED FOR OBJECT DETECTOR, BY USING DEEP ENCODER AND ACTIVE LEARNING DEVICE USING THE SAME 审中-公开

    公开(公告)号：WO2021225296A1

    公开(公告)日：2021-11-11

    申请号：PCT/KR2021/004757

    申请日：2021-04-15

    Applicant: STRADVISION, INC.

    Inventor： KIM, Kye-Hyeon ,  JE, Hongmo ,  KIM, Yongjoong ,  RYU, Wooju

    IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063

    Abstract: A method for explainable active learning, to be used for an object detector, by using a deep autoencoder is provided. The method includes steps of an active learning device (a) (i) inputting acquired test images into the object detector to detect objects and output bounding boxes, (ii) cropping regions, corresponding to the bounding boxes, in the test images, (iii) resizing the test images and the cropped images into a same size, and (iv) inputting the resized images into a data encoder of the deep autoencoder to output data codes, and (b) (i) confirming reference data codes corresponding to the number of the resized images less than a counter threshold by referring to a data codebook, (ii) extracting specific data codes from the data codes, (iii) selecting specific test images as rare samples, and (iv) updating the data codebook by referring to the specific data codes.

    METHOD FOR PERFORMING CONTINUAL LEARNING ON CLASSIFIER IN CLIENT CAPABLE OF CLASSIFYING IMAGES BY USING CONTINUAL LEARNING SERVER AND CONTINUAL LEARNING SERVER USING THE SAME
    6.
    发明申请
    METHOD FOR PERFORMING CONTINUAL LEARNING ON CLASSIFIER IN CLIENT CAPABLE OF CLASSIFYING IMAGES BY USING CONTINUAL LEARNING SERVER AND CONTINUAL LEARNING SERVER USING THE SAME 审中-公开

    公开(公告)号：WO2021221254A1

    公开(公告)日：2021-11-04

    申请号：PCT/KR2020/016418

    申请日：2020-11-19

    Applicant: STRADVISION, INC.

    Inventor： YU, Dongkyu ,  JE, Hongmo ,  KANG, Bongnam ,  RYU, Wooju

    IPC: G06N3/08 ,  G06N20/00

    Abstract: A method for performing continual learning on a classifier, in a client, capable of classifying images by using a continual learning server is provided. The method includes steps of: a continual learning server (a) inputting first hard images from a first classifier of a client into an Adversarial Autoencoder, to allow an encoder to output latent vectors from the first hard images, allow a decoder to output reconstructed images from the latent vectors, and allow a discriminator and a second classifier to output attribute and classification information to determine second hard images to be stored in a first training data set, and generating augmented images to be stored in a second training data set by adjusting the latent vectors of the reconstructed images determined not as the second hard images; (b) continual learning a third classifier corresponding to the first classifier; and (c) transmitting updated parameters to the client.

Patent Agency Ranking