US 12,347,171 B2
Model update method and related apparatus
Jifei Han, Shenzhen (CN); Zhilan Hu, Beijing (CN); and Bo Bai, Beijing (CN)
Assigned to Huawei Technologies Co., Ltd., Shenzhen (CN)
Filed by HUAWEI TECHNOLOGIES CO., LTD., Shenzhen (CN)
Filed on Aug. 30, 2022, as Appl. No. 17/898,948.
Application 17/898,948 is a continuation of application No. PCT/CN2021/079005, filed on Mar. 4, 2021.
Claims priority of application No. 202010143004.0 (CN), filed on Mar. 4, 2020.
Prior Publication US 2022/0415023 A1, Dec. 29, 2022
Int. Cl. G06K 9/00 (2022.01); G06V 10/74 (2022.01); G06V 10/762 (2022.01); G06V 10/774 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01)
CPC G06V 10/774 (2022.01) [G06V 10/761 (2022.01); G06V 10/762 (2022.01); G06V 10/776 (2022.01); G06V 10/82 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A model update method, comprising:
obtaining a neural network model and a plurality of training images;
performing feature extraction on the plurality of training images by using the neural network model to obtain a plurality of target features;
performing a plurality of times of first clustering processing on the plurality of training images based on the plurality of target features to obtain a plurality of first clustering results, wherein each first clustering result of the plurality of first clustering results corresponds to one silhouette coefficient, and the silhouette coefficient indicates clustering quality related to a degree of inter-category separation and a degree of intra-category cohesion;
determining a first target clustering result from the plurality of first clustering results based on a plurality of silhouette coefficients corresponding to the plurality of first clustering results, wherein the first target clustering result comprises M clustering categories; and
performing second clustering processing on the plurality of training images based on the plurality of target features to obtain a second clustering result, and updating a parameter of the neural network model according to a first loss function, wherein a quantity of clustering categories comprised in the second clustering result is M.