Patents by Inventor Hasnain Raza

Hasnain Raza 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).

  • Weakly supervised one-shot image segmentation
    Patent number: 11816188
    Abstract: A machine learning model may be trained based on a training set including training images depicting various base objects. Each training images may be associated with a ground-truth segmentation corresponding to one or more pixel-wise labels. The machine learning model may be trained to learn base class prototypes corresponding to segmentations of classes of similar base objects. The machine learning model may be further trained based on a support image depicting a novel object. The support image may be associated with an image-level label corresponding to the novel object. The machine learning model may be trained to learn, based on a base class prototype identified as being similar to the support image, a novel class prototype corresponding to the novel object. The trained machine learning model to may be applied to segment a query image. Related systems and computer program products are also provided.
    Type: Grant
    Filed: August 31, 2020
    Date of Patent: November 14, 2023
    Assignee: SAP SE
    Inventors: Moin Nabi, Tassilo Klein, Hasnain Raza, Sayyed Mahdyar Ravanbakhsh
  • WEAKLY SUPERVISED ONE-SHOT IMAGE SEGMENTATION
    Publication number: 20220067455
    Abstract: A machine learning model may be trained based on a training set including training images depicting various base objects. Each training images may be associated with a ground-truth segmentation corresponding to one or more pixel-wise labels. The machine learning model may be trained to learn base class prototypes corresponding to segmentations of classes of similar base objects. The machine learning model may be further trained based on a support image depicting a novel object. The support image may be associated with an image-level label corresponding to the novel object. The machine learning model may be trained to learn, based on a base class prototype identified as being similar to the support image, a novel class prototype corresponding to the novel object. The trained machine learning model to may be applied to segment a query image. Related systems and computer program products are also provided.
    Type: Application
    Filed: August 31, 2020
    Publication date: March 3, 2022
    Inventors: Moin Nabi, Tassilo Klein, Hasnain Raza, Sayyed Mahdyar Ravanbakhsh