US 11,817,206 B2
Detection model training method and apparatus, and terminal device
Chen Cheng, Shenzhen (CN); Zhongqian Sun, Shenzhen (CN); Hao Chen, Shenzhen (CN); and Wei Yang, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on Mar. 21, 2022, as Appl. No. 17/699,801.
Application 17/699,801 is a continuation of application No. 17/084,475, filed on Oct. 29, 2020, granted, now 11,315,677.
Application 17/084,475 is a continuation of application No. PCT/CN2019/090521, filed on Jun. 10, 2019.
Claims priority of application No. 201811251214.0 (CN), filed on Oct. 25, 2018.
Prior Publication US 2022/0208357 A1, Jun. 30, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06K 9/00 (2022.01); G16H 30/40 (2018.01); G16H 30/20 (2018.01); G16H 50/20 (2018.01); G06N 3/08 (2023.01); G06F 18/24 (2023.01); G06F 18/213 (2023.01); G06F 18/214 (2023.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G06V 10/44 (2022.01)
CPC G16H 30/40 (2018.01) [G06F 18/213 (2023.01); G06F 18/214 (2023.01); G06F 18/24 (2023.01); G06N 3/08 (2013.01); G06V 10/454 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G16H 30/20 (2018.01); G16H 50/20 (2018.01)] 20 Claims
OG exemplary drawing
 
13. A terminal device, comprising a processor and a storage medium, the processor being configured to implement instructions; and
the storage medium being configured to store a plurality of instructions, the instructions being loaded by the processor to perform:
determining an initial training model, the initial training model comprising an initial detection model and an adaptive model;
obtaining a training sample, the training sample comprising source domain data and target domain data, the source domain data comprising a plurality of first images, a first image comprising: a first identifier indicating whether a target object is present, and a second identifier indicating a domain that the first image belongs to; the target domain data comprising: a plurality of second images, and a second image comprising a third identifier indicating a domain that the second image belongs to;
determining whether a target object is present in a first image through the initial detection model according to a feature of the first image, to obtain a detection result; and determining a domain that an image in the training sample belongs to through the adaptive model according to a feature of the image, to obtain a domain classification result;
calculating a loss function value related to the initial training model according to the detection result, the domain classification result, the first identifier, the second identifier, and the third identifier; and
adjusting a parameter value in the initial training model according to the loss function value, to obtain a final detection model.