Patents by Inventor Anthony Lem

Anthony Lem 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).

  • Semantic input sampling for explanation (SISE) of convolutional neural networks
    Patent number: 11809519
    Abstract: Embodiments of the present disclosure relate to generating explanation maps for explaining convolutional neural networks through attribution-based input sampling and block-wise feature aggregation. An example of a disclosed method for generating an explanation map for a convolutional neural network (CNN) includes obtaining an input image resulting in an output determination of the CNN, selecting a plurality of feature maps extracted from a plurality of pooling layers of the CNN, generating a plurality of attribution masks based on the plurality of feature maps, applying the generated attribution masks to the input image to obtain a plurality of visualization maps, and generating an explanation map of the output determination of the CNN based on the plurality of visualization maps.
    Type: Grant
    Filed: August 18, 2021
    Date of Patent: November 7, 2023
    Assignees: LG ELECTRONICS INC., The Governing Council of the University of Toronto
    Inventors: Jongseong Jang, Hyunwoo Kim, YeonJeong Jeong, SangMin Lee, Sam Sattarzadeh, Mahesh Sudhakar, Shervin Mehryar, Anthony Lem, Konstantinos Plataniotis
  • SEMANTIC INPUT SAMPLING FOR EXPLANATION (SISE) OF CONVOLUTIONAL NEURAL NETWORKS
    Publication number: 20220058431
    Abstract: Embodiments of the present disclosure relate to generating explanation maps for explaining convolutional neural networks through attribution-based input sampling and block-wise feature aggregation. An example of a disclosed method for generating an explanation map for a convolutional neural network (CNN) includes obtaining an input image resulting in an output determination of the CNN, selecting a plurality of feature maps extracted from a plurality of pooling layers of the CNN, generating a plurality of attribution masks based on the plurality of feature maps, applying the generated attribution masks to the input image to obtain a plurality of visualization maps, and generating an explanation map of the output determination of the CNN based on the plurality of visualization maps.
    Type: Application
    Filed: August 18, 2021
    Publication date: February 24, 2022
    Applicants: LG ELECTRONICS INC., The Governing Council of the University of Toronto
    Inventors: Jongseong Jang, Hyunwoo Kim, YeonJeong Jeong, SangMin Lee, Sam Sattarzadeh, Mahesh Sudhakar, Shervin Mehryar, Anthony Lem, Konstantinos Plataniotis