公开(公告)号：US20250148186A1

公开(公告)日：2025-05-08

申请号：US19011809

申请日：2025-01-07

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Shoubo HU ,  Zhitang CHEN ,  Xiaopeng ZHANG ,  Shengyu ZHU ,  Pengyun LI ,  Jianxin MIAO ,  Yu HUANG

IPC: G06F30/398 ,  G06F111/08 ,  G06N3/0455

Abstract: This application relates to a method and an apparatus for determining a root-cause defect, and a storage medium. The method includes: obtaining a layout of a chip and diagnosis information of a defect in the chip; determining first feature information based on the layout and the diagnosis information; and determining, based on the first feature information by using a neural network model. With the described technology, both a design defect and a manufacturing defect of a chip can be considered, so that inference for a root cause is more comprehensive. In addition, an interaction relationship between complex root causes can be considered, so that a root-cause defect determined through inference is more accurate. In this way, assistance can be better provided in subsequent improvement of a chip-related design or a manufacturing technique, to reduce an increase in costs caused by a low yield rate.

公开(公告)号：US20230075836A1

公开(公告)日：2023-03-09

申请号：US17986081

申请日：2022-11-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Fuhui TANG ,  Xiaopeng ZHANG ,  Minzhe NIU ,  Zichen WANG ,  Jianhua HAN ,  Qi TIAN

IPC: G06V10/774 ,  G06V10/40 ,  G06V10/82 ,  G06V10/764

Abstract: A model training method and a related apparatus are provided, which may be used in computer vision to perform image detection. The method includes: extracting feature information in a target image; further separately extracting features of a target object from the feature information by using a Gaussian mask to obtain a first local feature and a second local feature; determining a feature loss by using the first local feature and the second local feature; performing prediction by using the first network and the second network based on a same region proposal set to obtain a first classification predicted value and a second classification predicted value, and obtaining a classification loss based on the first classification predicted value and the second classification predicted value; and training the second network based on the classification loss and the feature loss to obtain a target network.

公开(公告)号：US20220148328A1

公开(公告)日：2022-05-12

申请号：US17586136

申请日：2022-01-27

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Qixiang YE ,  Tianliang ZHANG ,  Jianzhuang LIU ,  Xiaopeng ZHANG ,  QI TIAN ,  Lihui JIANG

IPC: G06V40/10 ,  G06V10/25 ,  G06V10/80 ,  G06V10/77 ,  G06V10/44 ,  G06V10/82 ,  G06V20/58 ,  G06V20/52

Abstract: This application relates to the field of artificial intelligence, and specifically, to the field of computer vision. The method includes: performing feature extraction on an image to obtain a basic feature map of the image; determining a proposal of a region possibly including a pedestrian in the image; processing the basic feature map of the image to obtain an object visibility map in which a response to a pedestrian visible part is greater than a response to a pedestrian blocked part and a background part; performing weighted summation processing on the object visibility map and the basic feature map to obtain an enhanced feature map of the image; and determining, based on the proposal of the image and the enhanced feature map of the image, a bounding box including a pedestrian in the image and a confidence level of the bounding box including the pedestrian in the image.

公开(公告)号：US20220130142A1

公开(公告)日：2022-04-28

申请号：US17573220

申请日：2022-01-11

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yuhui XU ,  Lingxi XIE ,  Xiaopeng ZHANG ,  Xin CHEN ,  Guojun QI ,  QI TIAN

IPC: G06V10/82 ,  G06V10/764 ,  G06N3/10 ,  G06N3/08

Abstract: Example neural architecture search methods and image processing methods and apparatuses in the field of computer vision in the field of artificial intelligence are provided. The example neural architecture search method includes determining search space and a plurality of construction units, superimposing the plurality of construction units to obtain a search network, adjusting, in the search space, network architectures of the construction units in the search network, to obtain optimized construction units, and establishing a target neural network based on the optimized construction units. In each construction unit, some channels of an output feature map of each node are processed by using a to-be-selected operation to obtain a processed feature map, and the processed feature map and a remaining feature map are stitched and then input to a next node.