US 12,039,440 B2
Image classification method and apparatus, and image classification model training method and apparatus
Weiran Huang, Beijing (CN); Aoxue Li, Beijing (CN); Zhenguo Li, Hong Kong (CN); Tiange Luo, Beijing (CN); and Liwei Wang, Beijing (CN)
Assigned to Huawei Technologies Co., Ltd., Shenzhen (CN); and Peking University, Beijing (CN)
Filed by Huawei Technologies Co., Ltd., Shenzhen (CN); and Peking University, Beijing (CN)
Filed on Jan. 24, 2022, as Appl. No. 17/582,880.
Application 17/582,880 is a continuation of application No. PCT/CN2020/102741, filed on Jul. 17, 2020.
Claims priority of application No. 201910672533.7 (CN), filed on Jul. 24, 2019.
Prior Publication US 2022/0148291 A1, May 12, 2022
Int. Cl. G06V 10/774 (2022.01); G06N 3/045 (2023.01); G06N 3/08 (2023.01); G06V 10/82 (2022.01)
CPC G06N 3/08 (2013.01) [G06N 3/045 (2023.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)] 30 Claims
OG exemplary drawing
 
1. An image classification method, applied to an image classification apparatus comprising a processor and a memory, the method comprising:
obtaining a to-be-processed image; and
classifying the to-be-processed image, based on a preset global class feature, to obtain a classification result of the to-be-processed image,
wherein the preset global class feature comprises a plurality of class features obtained through training based on a plurality of training images in a training set,
wherein the plurality of class features in the preset global class feature are used to indicate visual features of all classes in the training set,
wherein all the classes in the training set are classes to which all the training images in the training set belong, and
wherein the training set comprises images in a base class and images in a novel class.