Title:
画像検索のためのニューラルネットワークのトレーニング方法、装置および電子装置
Document Type and Number:
Japanese Patent JP7438591
Kind Code:
B2
Abstract:
Provided are a neural network training method and apparatus for image retrieval, and an electronic device. A neural network comprises: one feature extractor and a plurality of learners. The method comprises: for each training image group, inputting three images of the training image group into the feature extractor, and determining features of the three images (501); for each image in each training image group, respectively multiplying the features of the image by a random weight corresponding to each learner, so as to obtain weighted features corresponding to each learner (502); for each image in each training image group, inputting the weighted features of the image corresponding to each learner into the corresponding learner, and determining a plurality of feature vectors of the image (503); and adjusting parameters of the neural network on the basis of the plurality of feature vectors of each image in a plurality of training image groups (504). The influence of information differences between training data on a network is weakened.
Inventors:
Ren Hao
Siyoung Lee
road red
Siyoung Lee
road red
Application Number:
JP2023509754A
Publication Date:
February 27, 2024
Filing Date:
August 25, 2020
Export Citation:
Assignee:
UISEE TECHNOLOGIES (ZHEJIANG) LTD.
International Classes:
G06F16/53; G06T7/00; G06F16/56; G06N3/045; G06N3/09; G06V10/778; G06V10/82
Foreign References:
| CN111242162A | ||||
| CN111125396A | ||||
| CN107092661A | ||||
| CN108021947A | ||||
| CN110688502A | ||||
| US20190377930 |
Attorney, Agent or Firm:
Patent Attorney Corporation Junias International Patent Office