知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

4 records (took 0.017 seconds)

    Systems, methods, and apparatuses for actively and continually fine-tuning convolutional neural networks to reduce annotation requirements
    1.
    发明授权
    Systems, methods, and apparatuses for actively and continually fine-tuning convolutional neural networks to reduce annotation requirements 有权

    公开(公告)号：US12216737B2

    公开(公告)日：2025-02-04

    申请号：US17698805

    申请日：2022-03-18

    Applicant: Arizona Board of Regents on behalf of Arizona State University

    Inventor： Zongwei Zhou ,  Jae Shin ,  Jianming Liang

    IPC: G06V10/82 ,  G06F18/21 ,  G06F18/214 ,  G06T7/00 ,  G06V10/764 ,  G16H30/40

    Abstract: Described herein are systems, methods, and apparatuses for actively and continually fine-tuning convolutional neural networks to reduce annotation requirements, in which the trained networks are then utilized in the context of medical imaging. The success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, it is tedious, laborious, and time consuming to create large annotated datasets, and demands costly, specialty-oriented skills. A novel method to naturally integrate active learning and transfer learning (fine-tuning) into a single framework is presented to dramatically reduce annotation cost, starting with a pre-trained CNN to seek “worthy” samples for annotation and gradually enhances the (fine-tuned) CNN via continual fine-tuning. The described method was evaluated using three distinct medical imaging applications, demonstrating that it can reduce annotation efforts by at least half compared with random selection.

    Methods, systems, and media for selecting candidates for annotation for use in training classifiers
    2.
    发明授权
    Methods, systems, and media for selecting candidates for annotation for use in training classifiers 有权

    公开(公告)号：US10956785B2

    公开(公告)日：2021-03-23

    申请号：US16397990

    申请日：2019-04-29

    Applicant: ARIZONA BOARD OF REGENTS ON BEHALF OF ARIZONA STATE UNIVERSITY

    Inventor： Jianming Liang ,  Zongwei Zhou ,  Jae Shin

    IPC: G06K9/00 ,  G06K9/62

    Abstract: Methods, systems, and media for selecting candidates for annotation for use in training classifiers are provided. In some embodiments, the method comprises: identifying, for a trained Convolutional Neural Network (CNN), a group of candidate training samples, wherein each candidate training sample includes a plurality of patches; for each patch of the plurality of patches, determining a plurality of probabilities, each probability being a probability that the patch corresponds to a label of a plurality of labels; identifying a subset of the patches in the plurality of patches; for each patch in the subset of the patches, calculating a metric that indicates a variance of the probabilities assigned to each patch; selecting a subset of the candidate training samples based on the metric; labeling candidate training samples in the subset of the candidate training samples by querying an external source; and re-training the CNN using the labeled candidate training samples.

    SYSTEMS, METHODS, AND APPARATUSES FOR ACTIVELY AND CONTINUALLY FINE-TUNING CONVOLUTIONAL NEURAL NETWORKS TO REDUCE ANNOTATION REQUIREMENTS
    4.
    发明申请
    SYSTEMS, METHODS, AND APPARATUSES FOR ACTIVELY AND CONTINUALLY FINE-TUNING CONVOLUTIONAL NEURAL NETWORKS TO REDUCE ANNOTATION REQUIREMENTS 有权

    公开(公告)号：US20220300769A1

    公开(公告)日：2022-09-22

    申请号：US17698805

    申请日：2022-03-18

    Applicant: Arizona Board of Regents on behalf of Arizona State University

    Inventor： Zongwei Zhou ,  Jae Shin ,  Jianming Liang

    IPC: G06K9/62 ,  G16H30/40 ,  G06V10/82 ,  G06V10/764 ,  G06T7/00

    Abstract: Described herein are systems, methods, and apparatuses for actively and continually fine-tuning convolutional neural networks to reduce annotation requirements, in which the trained networks are then utilized in the context of medical imaging. The success of convolutional neural networks (CNNs) in computer vision is largely attributable to the availability of massive annotated datasets, such as ImageNet and Places. However, it is tedious, laborious, and time consuming to create large annotated datasets, and demands costly, specialty-oriented skills. A novel method to naturally integrate active learning and transfer learning (fine-tuning) into a single framework is presented to dramatically reduce annotation cost, starting with a pre-trained CNN to seek “worthy” samples for annotation and gradually enhances the (fine-tuned) CNN via continual fine-tuning. The described method was evaluated using three distinct medical imaging applications, demonstrating that it can reduce annotation efforts by at least half compared with random selection.

Patent Agency Ranking