Patents by Inventor Pablo Navarre Michelini

Pablo Navarre Michelini has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Computer-implemented method of training convolutional neural network, convolutional neural network, computer-implemented method using convolutional neural network, apparatus for training convolutional neural network, and computer-program product
    Patent number: 11537849
    Abstract: A computer-implemented method of training a convolutional neural network configured to morph content features of an input image with style features of a style image is provided. The computer-implemented method includes selecting a training style image; extracting style features of the training style image; selecting a training content image; extracting content features of the training content image; processing the training content image through the convolutional neural network to generate a training output image including the content features of the training content image morphed with the style features of the training style image; extracting content features and style features of the training output image; computing a total loss; and tuning the convolutional neural network based on the total loss including a content loss, a style loss, and a regularization loss.
    Type: Grant
    Filed: July 22, 2019
    Date of Patent: December 27, 2022
    Assignee: BOE Technology Group Co., Ltd.
    Inventors: Dan Zhu, Lijie Zhang, Pablo Navarre Michelini, Hanwen Liu
  • COMPUTER-IMPLEMENTED METHOD OF TRAINING CONVOLUTIONAL NEURAL NETWORK, CONVOLUTIONAL NEURAL NETWORK, COMPUTER-IMPLEMENTED METHOD USING CONVOLUTIONAL NEURAL NETWORK, APPARATUS FOR TRAINING CONVOLUTIONAL NEURAL NETWORK, AND COMPUTER-PROGRAM PRODUCT
    Publication number: 20210012181
    Abstract: A computer-implemented method of training a convolutional neural network configured to morph content features of an input image with style features of a style image is provided. The computer-implemented method includes selecting a training style image; extracting style features of the training style image; selecting a training content image; extracting content features of the training content image; processing the training content image through the convolutional neural network to generate a training output image including the content features of the training content image morphed with the style features of the training style image; extracting content features and style features of the training output image; computing a total loss; and tuning the convolutional neural network based on the total loss including a content loss, a style loss, and a regularization loss.
    Type: Application
    Filed: July 22, 2019
    Publication date: January 14, 2021
    Applicant: BOE Technology Group Co., Ltd.
    Inventors: Dan Zhu, Lijie Zhang, Pablo Navarre Michelini, Hanwen Liu