METHOD AND DEVICE FOR TRAINING IMAGE RECOGNITION MODEL, METHOD AND DEVICE FOR RECOGNIZING IMAGE, ELECTRONIC DEVICE, STORAGE MEDIUM, AND COMPUTER PROGRAM

To provide a method and device for training an image recognition model configured to reduce the amount of manual annotation, thereby improving performance of the model, and a method and device for recognizing an image.SOLUTION: A method comprises: obtaining a sample set with labels, a sample set wit...

Full description

Saved in:
Bibliographic Details
Main Authors GUO RUOYU, DU YUNING, ZHAO QIAO, LIU QIWEN, LI CHENXIA, GAO TINGQUAN, YU DIANHAI, HU XIAOGUANG, BI RAN, MA YANJUN
Format Patent
LanguageEnglish
Japanese
Published 12.04.2022
Subjects
Online AccessGet full text

Cover

Loading…
More Information
Summary:To provide a method and device for training an image recognition model configured to reduce the amount of manual annotation, thereby improving performance of the model, and a method and device for recognizing an image.SOLUTION: A method comprises: obtaining a sample set with labels, a sample set without labels and a knowledge distillation network; and executing the following training steps: selecting input samples from the sample set with labels and the sample set without labels, and accumulating the number of iterations; respectively inputting the input samples into a student network and a teacher network of the knowledge distillation network, and training the student network and the teacher network; and if the training completion condition is satisfied, selecting an image recognition model from the student network and the teacher network.SELECTED DRAWING: Figure 2 【課題】人手によるアノテーションの量を減らし、モデルの性能を向上させることができる画像認識モデルをトレーニングするための方法及び装置並びに画像を認識するための方法及び装置を提供する。【解決手段】方法は、タグ付きサンプルセットと、タグなしサンプルセットと、知識蒸留ネットワークと、を取得し、トレーニングステップを実行することを含む。トレーニングステップは、タグ付きサンプルセットとタグなしサンプルセットから入力サンプルを選択し、かつ、反復回数を累加することと、入力サンプルをそれぞれ知識蒸留ネットワークの学生ネットワークと教師ネットワークに入力し、学生ネットワークと教師ネットワークをトレーニングすることと、トレーニング完了の条件を満たす場合、学生ネットワークと教師ネットワークの中から画像認識モデルを選択することと、を含む。【選択図】図2
Bibliography:Application Number: JP20220017229