US 11,929,871 B2
Method for generating backbone network, apparatus for generating backbone network, device, and storage medium
Cheng Cui, Beijing (CN); Tingquan Gao, Beijing (CN); Shengyu Wei, Beijing (CN); Yuning Du, Beijing (CN); Ruoyu Guo, Beijing (CN); Bin Lu, Beijing (CN); Ying Zhou, Beijing (CN); Xueying Lyu, Beijing (CN); Qiwen Liu, Beijing (CN); Xiaoguang Hu, Beijing (CN); Dianhai Yu, Beijing (CN); and Yanjun Ma, Beijing (CN)
Filed by Beijing Baidu Netcom Science Technology Co., Ltd., Beijing (CN)
Filed on Apr. 11, 2022, as Appl. No. 17/718,149.
Claims priority of application No. 202111088473.8 (CN), filed on Sep. 16, 2021.
Prior Publication US 2022/0247626 A1, Aug. 4, 2022
Int. Cl. G06K 9/62 (2022.01); G06F 18/214 (2023.01); H04L 41/0806 (2022.01); H04L 41/084 (2022.01); H04L 41/0894 (2022.01)
CPC H04L 41/0806 (2013.01) [G06F 18/214 (2023.01); H04L 41/0846 (2013.01); H04L 41/0894 (2022.05)] 18 Claims
OG exemplary drawing
 
1. A method for generating a backbone network, comprising:
acquiring a set of training images, a set of inference images, and a set of initial backbone networks;
training and inferring, for each initial backbone network in the set of initial backbone networks, using the set of training images and the set of inference images to obtain an inference time and an inference accuracy of a trained backbone network in an inference process, wherein training and inferring, for each initial backbone network in the set of initial backbone networks, comprises:
training an initial backbone network by using the set of training images to obtain the trained backbone network, and
converting the trained backbone network into an inference network, inferring the set of inference images by using the inference network, and obtaining the inference time and the inference accuracy of the inference network in the inference process, wherein the inference time is a time used for inferring the set of inference images by using the inference network, and the inference accuracy is an accuracy of an inference result of the inference network; and
determining a basic backbone network based on the inference time and the inference accuracy of the trained backbone network in the inference process, wherein determining the basic backbone network comprises:
determining, based on the inference accuracy and the inference time of each inference network converted from the set of initial backbone networks, the basic backbone network from the set of initial backbone networks; and
obtaining a target backbone network based on the basic backbone network and a preset target network.