公开(公告)号：US20230401838A1

公开(公告)日：2023-12-14

申请号：US18455918

申请日：2023-08-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xinghao CHEN ,  Wenshuo LI ,  Yunhe WANG ,  Chunjing XU

IPC: G06V10/82 ,  G06V10/77 ,  G06V10/80

CPC classification number: G06V10/82 ,  G06V10/7715 ,  G06V10/803

Abstract: An image processing method is disclosed in embodiments of this disclosure and is applied to the field of artificial intelligence. The method includes: obtaining an input feature map of an image to be processed, where the input feature map includes a first input sub-feature map and a second input sub-feature map, and resolution of the first input sub-feature map is higher than resolution of the second input sub-feature map; performing feature fusion processing on the input feature map by using a target network, to obtain an output feature map, where a feature of the first input sub-feature map is fused to a feature of the second input sub-feature map from a low level to a high level in the target network; and performing, based on the output feature map, object detection on the image to be processed, to obtain an object detection result.

公开(公告)号：US20230153615A1

公开(公告)日：2023-05-18

申请号：US18147297

申请日：2022-12-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yixing XU ,  Xinghao CHEN ,  Yunhe WANG ,  Chunjing XU

IPC: G06N3/08 ,  G06N3/045

CPC classification number: G06N3/08 ,  G06N3/045

Abstract: The technology of this application relates to a neural network distillation method, applied to the field of artificial intelligence, and includes processing to-be-processed data by using a first neural network and a second neural network to obtain a first target output and a second target output, where the first target output is obtained by performing kernel function-based transformation on an output of the first neural network layer, and the second target output is obtained by performing kernel function-based transformation on an output of the second neural network layer. The method further includes performing knowledge distillation on the first neural network based on a target loss constructed by using the first target output and the second target output.

公开(公告)号：US20210312261A1

公开(公告)日：2021-10-07

申请号：US17220158

申请日：2021-04-01

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yixing XU ,  Kai HAN ,  Yunhe WANG ,  Chunjing XU ,  Qi TIAN

IPC: G06N3/04 ,  G06N3/08

Abstract: The present application discloses a neural network search method in the field of artificial intelligence, and the neural network search method includes: obtaining a feature tensor of each of a plurality of neural networks, where the feature tensor of each neural network is used to represent a computing capability of the neural network; inputting the feature tensor of each of the plurality of neural networks into an accuracy prediction model for calculation, to obtain accuracy of each neural network, where the accuracy prediction model is obtained through training based on a ranking-based loss function; and determining a neural network corresponding to the maximum accuracy as a target neural network. Embodiments of the present invention help improve accuracy of a network structure found through search.

公开(公告)号：US20250014324A1

公开(公告)日：2025-01-09

申请号：US18894274

申请日：2024-09-24

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Wenshuo LI ,  Hanting CHEN ,  Jianyuan GUO ,  Ziyang ZHANG ,  Yunhe WANG

IPC: G06V10/82 ,  G06V10/776

Abstract: An image processing method, a neural network training method, and a related device are provided. The method may apply an artificial intelligence technology to the image processing field. The method includes: performing feature extraction on a to-be-processed image by using a first neural network, to obtain feature information of the to-be-processed image. The performing feature extraction on a to-be-processed image by using a first neural network includes: obtaining first feature information corresponding to the to-be-processed image, where the to-be-processed image includes a plurality of image blocks, and the first feature information includes feature information of the image block; sequentially inputting feature information of at least two groups of image blocks into an LIF module, to obtain target data generated by the LIF module; and obtaining, based on the target data, updated feature information of the to-be-processed image including the image block.

公开(公告)号：US20240185573A1

公开(公告)日：2024-06-06

申请号：US18441229

申请日：2024-02-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Han SHU ,  Jiahao WANG ,  Hanting CHEN ,  Wenshuo LI ,  Yunhe WANG

IPC: G06V10/77 ,  G06V10/764 ,  G06V10/80 ,  G06V10/82

CPC classification number: G06V10/7715 ,  G06V10/764 ,  G06V10/806 ,  G06V10/82

Abstract: This disclosure provides an image classification method and a related device thereof. The method includes the following operations: After obtaining a target image, a transformer network may perform linear transformation processing based on the target image to obtain a Q-feature, a K-feature, and a V-feature. The transformer network calculates a distance between the Q-feature and the K-feature to obtain an attention feature. Then, the transformer network performs fusion processing on the attention feature and the V-feature, and obtains a classification result of the target image based on a fused feature.

公开(公告)号：US20230401446A1

公开(公告)日：2023-12-14

申请号：US18238016

申请日：2023-08-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yehui TANG ,  Yixing XU ,  Yunhe WANG ,  Chunjing XU

IPC: G06N3/082 ,  G06N3/0464

CPC classification number: G06N3/082 ,  G06N3/0464 ,  G06V10/82

Abstract: Embodiments of this application disclose a convolutional neural network pruning processing method, a data processing method, and a device, which may be applied to the field of artificial intelligence. The convolutional neural network pruning processing method includes: performing sparse training on a convolutional neural network by using a constructed objective loss function, where the objective loss function may include three sub-loss functions.

公开(公告)号：US20230177641A1

公开(公告)日：2023-06-08

申请号：US18147371

申请日：2022-12-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Dehua SONG ,  Yunhe WANG ,  Hanting CHEN ,  Chunjing XU

IPC: G06T3/40 ,  G06T5/00 ,  G06T5/20

CPC classification number: G06T3/4046 ,  G06T3/4015 ,  G06T3/4053 ,  G06T5/003 ,  G06T5/20 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A neural network training method, includes: obtaining an input feature map of a training image; performing feature extraction processing on the input feature map by using a feature extraction core of a neural network to obtain a first candidate feature map; adding the first candidate feature map and a second candidate feature map to obtain an output feature map, where the second candidate feature map is a feature map obtained after a value corresponding to each element in the input feature map is increased by N times, and N is greater than 0; determining an image processing result of the training image based on the output feature map; and adjusting a parameter of the neural network based on the image processing result.

公开(公告)号：US20220180199A1

公开(公告)日：2022-06-09

申请号：US17680630

申请日：2022-02-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yixing XU ,  Hanting CHEN ,  Kai HAN ,  Yunhe WANG ,  Chunjing XU

IPC: G06N3/08 ,  G06N3/04

Abstract: This application provides a neural network model compression method in the field of artificial intelligence. The method includes: obtaining, by a server, a first neural network model and training data of the first neural network that are uploaded by user equipment; obtaining a PU classifier based on the training data of the first neural network and unlabeled data stored in the server; selecting, by using the PU classifier, extended data from the unlabeled data stored in the server, where the extended data has a property and distribution similar to a property and distribution of the training data of the first neural network model; and training a second neural network model by using a knowledge distillation (KD) method based on the extended data, where the first neural network model is used as a teacher network model and the second neural network model is used as a student network model.

公开(公告)号：US20220157046A1

公开(公告)日：2022-05-19

申请号：US17587284

申请日：2022-01-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Hanting CHEN ,  Yunhe WANG ,  Chunjing XU

IPC: G06V10/764 ,  G06V10/77 ,  G06V10/82 ,  G06F17/16 ,  G06N3/02

Abstract: This application relates to an image recognition technology in the field of computer vision of artificial intelligence, and provides an image classification method and apparatus. The method includes: obtaining an input feature map of a to-be-processed image; performing feature extraction processing on the input feature map based on a feature extraction kernel of a neural network, to obtain an output feature map, where each of a plurality of output sub-feature maps is determined based on the corresponding input sub-feature map and the feature extraction kernel, at least one of the output sub-feature maps is determined based on a target matrix obtained after an absolute value is taken, and a difference between the target matrix and the input sub-feature map corresponding to the target matrix is the feature extraction kernel; and classifying the to-be-processed image based on the output feature map, to obtain a classification result of the to-be-processed image.

公开(公告)号：US20220019855A1

公开(公告)日：2022-01-20

申请号：US17488735

申请日：2021-09-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Hanting CHEN ,  Yunhe WANG ,  Chuanjian LIU ,  Kai HAN ,  Chunjing XU

IPC: G06K9/62 ,  G06N3/04

Abstract: The present application discloses an image generation method, a neural network compression method, and a related apparatus and device in the field of artificial intelligence. The image generation method includes: inputting a first matrix into an initial image generator to obtain a generated image; inputting the generated image into a preset discriminator to obtain a determining result, where the preset discriminator is obtained through training based on a real image and a category corresponding to the real image; updating the initial image generator based on the determining result to obtain a target image generator; and further inputting a second matrix into the target image generator to obtain a sample image. Further, a neural network compression method is disclosed, to compress the preset discriminator based on the sample image obtained by using the foregoing image generation method.