US 12,243,284 B2
Image classification method and apparatus
Kai Han, Beijing (CN); Yunhe Wang, Beijing (CN); Han Shu, Beijing (CN); and Chunjing Xu, Shenzhen (CN)
Assigned to Huawei Technologies Co., Ltd., Shenzhen (CN)
Filed by HUAWEI TECHNOLOGIES CO., LTD., Guangdong (CN)
Filed on Jan. 28, 2022, as Appl. No. 17/587,689.
Application 17/587,689 is a continuation of application No. PCT/CN2020/105830, filed on Jul. 30, 2020.
Claims priority of application No. 201910697287.0 (CN), filed on Jul. 30, 2019.
Prior Publication US 2022/0157041 A1, May 19, 2022
Int. Cl. G06V 10/00 (2022.01); G06V 10/44 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/454 (2022.01) [G06V 10/764 (2022.01); G06V 10/82 (2022.01)] 15 Claims
OG exemplary drawing
 
1. An image classification method, comprising:
obtaining an input feature map of a to-be-processed image;
performing convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain an intermediate feature map comprising M channels, wherein M is a positive integer;
performing convolution processing on the M channels of the intermediate feature map based on N matrices, to obtain an output feature map comprising N channels, wherein the N matrices represent N convolution kernels, the N matrices comprise M groups of convolution kernels, and the M groups of convolution kernels respectively correspond to the M channels of the intermediate feature map, and wherein a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and
classifying the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.