公开(公告)号：US20210406579A1

公开(公告)日：2021-12-30

申请号：US17468848

申请日：2021-09-08

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Tianwei Lin ,  Dongliang He ,  Fu Li

IPC: G06K9/34 ,  G06K9/62 ,  G06N3/04

Abstract: The present disclosure provides a model training method, an identification method, device, storage medium and program product, relating to computer vision technology and deep learning technology. In the solution provided by the present application, the image is deformed by the means of deforming the first training image without label itself, and the first unsupervised identification result is obtained by using the first model to identify the image before deformation, and the second unsupervised identification result is obtained by using the second model to identify the image after deformation, and the first unsupervised identification result of the first model is deformed, thus a consistency loss function can be constructed according to the second unsupervised identification result and the scrambled identification result. In this way, it is able to enhance the constraint effect of the consistency loss function and avoid destroying the scene semantic information of the images used for training.