US 12,322,156 B2
Input image size switchable network for adaptive runtime efficient image classification
Anbang Yao, Beijing (CN); Yikai Wang, Beijing (CN); Ming Lu, Beijing (CN); Shandong Wang, Beijing (CN); and Feng Chen, Shanghai (CN)
Assigned to Intel Corporation, Santa Clara, CA (US)
Appl. No. 17/918,080
Filed by Intel Corporation, Santa Clara, CA (US)
PCT Filed Jun. 15, 2020, PCT No. PCT/CN2020/096035
§ 371(c)(1), (2) Date Oct. 10, 2022,
PCT Pub. No. WO2021/253148, PCT Pub. Date Dec. 23, 2021.
Prior Publication US 2023/0343068 A1, Oct. 26, 2023
Int. Cl. G06V 10/764 (2022.01); G06V 10/32 (2022.01); G06V 10/44 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/764 (2022.01) [G06V 10/32 (2022.01); G06V 10/454 (2022.01); G06V 10/774 (2022.01); G06V 10/82 (2022.01)] 21 Claims
OG exemplary drawing
 
1. A system for image classification, the system comprising:
a non-transitory memory to store a first image at a first resolution and a second image at a second resolution less than the first resolution; and
one or more processors coupled to the memory, the one or more processors to:
apply a convolutional neural network layer to the first image or first feature maps corresponding to the first image using a plurality of convolutional layer parameters to generate one or more second feature maps corresponding to the first image;
perform a first normalization on the one or more second feature maps using a plurality of first normalization parameters to generate one or more third feature maps;
generate a first label for the first image using the one or more third feature maps;
apply the convolutional neural network layer to the second image or fourth feature maps corresponding to the second image using the plurality of convolutional layer parameters to generate one or more fifth feature maps corresponding to the second image;
perform a second normalization on the one or more fifth feature maps using a plurality of second normalization parameters exclusive of the first normalization parameters to generate one or more sixth feature maps; and
generate a second label for the second image using the one or more sixth feature maps.