公开(公告)号：US20250156697A1

公开(公告)日：2025-05-15

申请号：US19019769

申请日：2025-01-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xinghao CHEN ,  Zhijun TU ,  Yunhe WANG

IPC: G06N3/0495 ,  G06N3/084

Abstract: This application provides a binary quantization method, a neural network training method, a device, and a storage medium. The binary quantization method includes: determining to-be-quantized data in a neural network; determining a quantization parameter corresponding to the to-be-quantized data, where the quantization parameter includes a scaling factor and an offset; determining, based on the scaling factor and the offset, a binary upper limit and a binary lower limit corresponding to the to-be-quantized data; and performing binary quantization on the to-be-quantized data based on the scaling factor and the offset, to quantize the to-be-quantized data into the binary upper limit or the binary lower limit.

公开(公告)号：US20230401826A1

公开(公告)日：2023-12-14

申请号：US18456312

申请日：2023-08-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Jianyuan GUO ,  Kai HAN ,  Yunhe WANG ,  Chunjing XU

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

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

Abstract: This disclosure discloses a perception network. The perception network may be applied to the artificial intelligence field, and includes a feature extraction network. A first block in the feature extraction network is configured to perform convolution processing on input data, to obtain M target feature maps; at least one second block in the feature extraction network is configured to perform convolution processing on M1 target feature maps in the M target feature maps, to obtain M1 first feature maps; a target operation in the feature extraction network is used to process M2 target feature maps in the M target feature maps, to obtain M2 second feature maps; and a concatenation operation in the feature extraction network is used to concatenate the M1 first feature maps and the M2 second feature maps, to obtain a concatenated feature map.

公开(公告)号：US20220157041A1

公开(公告)日：2022-05-19

申请号：US17587689

申请日：2022-01-28

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Kai HAN ,  Yunhe WANG ,  Han SHU ,  Chunjing XU

IPC: G06V10/44 ,  G06V10/764 ,  G06V10/82

Abstract: This application relates to an image recognition technology in the field of computer vision in the field 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 convolution processing on the input feature map based on M convolution kernels of a neural network, to obtain a candidate output feature map of M channels, where M is a positive integer; performing matrix transformation on the M channels of the candidate output feature map based on N matrices, to obtain an output feature map of N channels, where a quantity of channels of each of the N matrices is less than M, N is greater than M, and N is a positive integer; and classify 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：US20250104397A1

公开(公告)日：2025-03-27

申请号：US18904682

申请日：2024-10-02

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Hanting CHEN ,  Yunhe WANG ,  Chunjing XU

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

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. An example method includes obtaining an input feature map of a to-be-processed image, and then 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. The to-be-processed image is classified based on the output feature map to obtain a classification result of the to-be-processed image.

公开(公告)号：US20240419947A1

公开(公告)日：2024-12-19

申请号：US18819957

申请日：2024-08-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xinghao CHEN ,  Yikai WANG ,  Xiudong WANG ,  Yunhe WANG

IPC: G06N3/0455

Abstract: Embodiments of this application disclose a data processing method. The method is used in a multimodal fusion scenario, and the method includes obtaining first data and second data, where modalities of the first data and the second data are different. The method also includes obtaining a first feature set of the first data and a second feature set of the second data, and replacing a first target feature in the first feature set with a second target feature in the second feature set, to obtain a third feature set, where the second target feature corresponds to the first target feature. The method further includes obtaining a data feature based on the third feature set and the second feature set, where the data feature is used to implement a computer vision task.

公开(公告)号：US20230306719A1

公开(公告)日：2023-09-28

申请号：US18203337

申请日：2023-05-30

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Tianyu GUO ,  Hanting CHEN ,  Yunhe WANG ,  Chunjing XU

IPC: G06V10/771 ,  G06T5/50 ,  G06T7/11 ,  G06V10/44

CPC classification number: G06V10/771 ,  G06T5/50 ,  G06T7/11 ,  G06V10/44 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221

Abstract: Embodiments of this application disclose a model structure, a method for training a model, an image enhancement method, and a device, and may be applied to the computer vision field in the artificial intelligence field. The model structure includes: a selection module, a plurality of first neural network layers, a segmentation module, a transformer module, a recombination module, and a plurality of second neural network layers. The model overcomes a limitation that the transformer module can only be used to process a natural language task, and may be applied to a low-level vision task. The model includes the plurality of first/second neural network layers, and different first/second neural network layers correspond to different image enhancement tasks. Therefore, after being trained, the model can be used to process different image enhancement tasks.

公开(公告)号：US20250095352A1

公开(公告)日：2025-03-20

申请号：US18962726

申请日：2024-11-27

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Kai HAN ,  Jianyuan GUO ,  Yehui TANG ,  Yunhe WANG

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

Abstract: This application discloses a visual task processing method and a related device thereof. A to-be-processed image can be processed using a target model, and features outputted by the target model can remain diversified, to help improve processing precision of a visual task for the to-be-processed image. The method in this application includes: obtaining a to-be-processed image; processing the to-be-processed image using a target model, to obtain a feature of the to-be-processed image, where the target model includes a first module and a second module connected to the first module, the first module includes a graph neural network, and the second module is configured to implement feature transformation; and completing a visual task for the to-be-processed image based on the feature of the to-be-processed image.

公开(公告)号：US20230351163A1

公开(公告)日：2023-11-02

申请号：US17733758

申请日：2022-04-29

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yehui TANG ,  Kai HAN ,  Jianyuan GUO ,  Yunhe WANG ,  Yanxi LI ,  Chang XU ,  Chao XU

IPC: G06N3/04 ,  G06K9/62

CPC classification number: G06N3/0481 ,  G06K9/6232 ,  G06K9/6261

Abstract: A method is provided for data processing based on a multi-layer perceptrons (MLP) architecture. The method comprises determining a plurality of tokens for a piece of data, generating an amplitude and a phase for each of the plurality of tokens, optimizing the plurality of tokens by mixing the plurality of tokens based on the amplitudes and the phases, and determining one or more features included in the piece of data based on the plurality of optimized tokens. Each token includes information associated with a segment of the piece of data.

公开(公告)号：US20200302265A1

公开(公告)日：2020-09-24

申请号：US16359346

申请日：2019-03-20

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Yunhe WANG ,  Chunjing XU ,  Kai HAN

IPC: G06N3/04 ,  G06F17/16 ,  G06F17/15

Abstract: This application discloses a convolutional neural network-based image processing method and image processing apparatus in the artificial intelligence field. The method may include: receiving an input image; preprocessing the input image to obtain preprocessed image information; and performing convolution on the image information using a convolutional neural network, and outputting a convolution result. In embodiments of this application, the image processing apparatus may store primary convolution kernels of convolution layers, and before performing convolution using the convolution layers, generate secondary convolution kernels using the primary convolution kernels of the convolution layers.

公开(公告)号：US20230419646A1

公开(公告)日：2023-12-28

申请号：US18237995

申请日：2023-08-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Kai HAN ,  Yunhe WANG ,  An XIAO ,  Jianyuan GUO ,  Chunjing XU ,  Li QIAN

IPC: G06V10/80 ,  G06V10/40 ,  G06V10/82

CPC classification number: G06V10/806 ,  G06V10/40 ,  G06V10/82

Abstract: Embodiments of this disclosure relate to the field of artificial intelligence, and disclose a feature extraction method and apparatus. The method includes: obtaining a to-be-processed object, and obtaining a segmented object based on the to-be-processed object, where the segmented object includes some elements in the to-be-processed object, a first vector indicates the segmented object, and a second vector indicates some elements in the segmented object; performing feature extraction on the first vector to obtain a first feature, and performing feature extraction on the second vector to obtain a second feature; fusing at least two second features based on a first target weight, to obtain a first fused feature; and performing fusion processing on the first feature and the first fused feature to obtain a second fused feature, where the second fused feature is used to obtain a feature of the to-be-processed object.