公开(公告)号：US20220309779A1

公开(公告)日：2022-09-29

申请号：US17703858

申请日：2022-03-24

Applicant: CANON KABUSHIKI KAISHA

Inventor： Deyu Wang ,  Dongchao Wen ,  Wei Tao ,  Lingxiao Yin

IPC: G06V10/96 ,  G06V10/82 ,  G06V10/766 ,  G06N3/08

Abstract: The invention provides a neural network training and application method, device and storage medium. The training method comprises: an obtaining step of obtaining a processing result and a loss function value of the processing result for at least one task after a sample image is processed in a neural network; wherein the neural network comprises at least one network structure; a determination step of determining importance of the processing result thereof based on the obtained loss function value; an adjustment step of adjusting a weight of the loss function for obtaining the loss function value based on the determined importance; and an update step of updating the neural network according to the loss function after the weight is adjusted.

公开(公告)号：US20240020519A1

公开(公告)日：2024-01-18

申请号：US18351417

申请日：2023-07-12

Applicant: CANON KABUSHIKI KAISHA

Inventor： Wei Tao ,  Tsewei Chen ,  Deyu Wang ,  Lingxiao Yin ,  Dongyue Zhao

IPC: G06N3/0495 ,  G06N3/084

CPC classification number: G06N3/0495 ,  G06N3/084

Abstract: The present disclosure provides training and application methods and apparatuses for a neural network model, and a storage medium. The training method includes: quantizing, in a forward transfer process, a network parameter represented by a continuous real value, and calculating a quantization error; determining, in a backward transfer process, a gradient of a weight in the neural network model; correcting the gradient of the weight based on the calculated quantization error, wherein the correcting includes correcting a magnitude of the gradient and correcting a direction of the gradient; and updating the neural network model according to the corrected gradient.