Huawei Technologies Co., Limited

Peking University

Zhenguo Li

Xing Zhang

Xiuqiang He

Wei Fan

Ke Yi

Ge Luo

Ruiming Tang

Liwei Wang

Aoxue Li

Weiran Huang

Huifeng Guo

Li Qian

Cheng He

Jiefeng Cheng

Hang Xu

Tiange Luo

Fei Chen

Bin Wu

Wei Zhang

Zhenhua Dong

Bin Liu

Gregory Gibran Slabaugh

Shuaihua Peng

Tom Ryder

Zhihong Zhao

Guilin Li

Zhen Yang

Shifeng Zhang

Xinyue Cai

Yimin Huang

Yujun Li

Niannan Xue

Steven George Mcdonagh

Sarah Parisot

Fengwei Zhou

Lin Lan

This application relates to the field of artificial intelligence, and discloses a data encoding method, a data decoding method, and data processing apparatuses. Both the data encoding method and the data decoding method relate to an invertible flow-based model. The invertible flow-based model includes a target invertible flow layer, a model parameter of the target invertible flow layer is used to constrain an auxiliary variable generated in an inverse transform processing process, an operation corresponding to the target invertible flow layer includes a multiplication operation and a division operation that are determined based on the model parameter, and the auxiliary variable is an increment of a product of the multiplication operation or a remainder generated through the division operation.

Data encoding method, data decoding method, and data processing apparatus

This application relates to the field of artificial intelligence. A recommendation method based on automatic feature grouping includes: obtaining a plurality of candidate recommended objects and a plurality of association features of each of the plurality of candidate recommended objects; performing multi-order automatic feature grouping on the plurality of association features of each candidate recommended object, to obtain a multi-order feature interaction set of each candidate recommended object; obtaining an interaction feature contribution value of each candidate recommended object through calculation based on the plurality of association features in the multi-order feature interaction set of each candidate recommended object; obtaining a prediction score of each candidate recommended object through calculation based on the interaction feature contribution value of each candidate recommended object; and determining one or more corresponding candidate recommended objects with a high prediction score as a target recommended object.

Recommendation method and apparatus based on automatic feature grouping

This application provides example object detection methods and apparatuses. This application relates to the field of artificial intelligence, and specifically, to the field of computer vision. One example method includes obtaining a to-be-detected image and performing convolution processing on the to-be-detected image to obtain an initial image feature of a to-be-detected object in the to-be-detected image. Based on knowledge graph information, an enhanced image feature of the to-be-detected object is determined. A candidate frame and a classification of the to-be-detected object is determined based on the initial image feature and the enhanced image feature of the to-be-detected object. The enhanced image feature indicates semantic information of a different object category corresponding to another object associated with the to-be-detected object.

Object detection method and apparatus, and computer storage medium

A neural network training method, an image classification system, and a related device, which may be applied to the artificial intelligence field. Feature extraction is performed on images in a training set (including a first set and a second set) by using a prototype network, to obtain first feature points, in a feature space, of a plurality of images in the first set and second feature points of a plurality of images in the second set. The first feature points are used for calculating a prototype of a class of an image, and the second feature points are used for updating a network parameter of the prototype network. A semantic similarity between classes of the images in the second set is obtained, to calculate a margin value between the classes of the images. Then, a loss function is adjusted based on the margin value.

Neural network training method, image classification system, and related device

The present disclosure relates to neural network optimization methods and apparatuses in the field of artificial intelligence. One example method includes sampling preset hyperparameter search space to obtain multiple hyperparameter combinations. Multiple iterative evaluations are performed on the multiple hyperparameter combinations to obtain multiple performance results of each hyperparameter combination. Any iterative evaluation comprises obtaining at least one performance result of each hyperparameter combination, and if a hyperparameter combination meets a first preset condition, re-evaluating the hyperparameter combination to obtain a re-evaluated performance result of the hyperparameter combination. An optimal hyperparameter combination is determined. If the optimal hyperparameter combination does not meet a second preset condition, a preset model is updated, based on the multiple performance results of each hyperparameter combination, for next sampling. Or if the optimal hyperparameter combination meets a second preset condition, the optimal hyperparameter combination is used as a hyperparameter combination of a neural network.

Neural network optimization method and apparatus

An image classification method, a neural network training method, and an apparatus are provided, and relate to the field of artificial intelligence, and specifically, to the field of computer vision. The image classification method includes: obtaining a to-be-processed image; and obtaining a classification result of the to-be-processed image based on a pre-trained neural network model, where the classification result includes a class or a superclass to which the to-be-processed image belongs. When the neural network model is trained, not only labels of a plurality of training images but also class hierarchy information of the plurality of training images is used. That is, more abundant information of the training images is used. Therefore, images can be better classified.

Image classification method, neural network training method, and apparatus

This disclosure discloses lane line detection methods and devices. In an implementation, features extracted by different layers of the neural network are fused to obtain a fused second feature map, so that the second feature map obtained through fusion processing has a plurality of layers of features. The fused second feature map has a related feature of a low-layer receptive field and a related feature of a high-layer receptive field. Afterwards, an output predicted lane line set is divided into groups, where each predicted lane line in each group has an optimal prediction interval.

Lane line detection method and related device

A processing entity generates a model for estimating scene illumination colour for a source image captured by a camera The processing entity acquires a set of images, captured by a respective camera, the set of images as a whole including images captured by multiple cameras; forms a set of tasks by assigning each image of the images set to a respective task such that images in the same task have in common that a the images are in a predetermined range; trains model parameters by repeatedly: selecting at least one of the tasks, forming an interim set of model parameters based on a first subset of the images of that task, estimating the quality of the interim set of model parameters against a second subset of the images of that task and updating the parameters of the model based on the interim set of parameters and the estimated quality.

Meta-learning for camera adaptive color constancy

Embodiments of the present invention provide a machine learning model training method, including: obtaining target task training data and N categories of support task training data; inputting the target task training data and the N categories of support task training data into a memory model to obtain target task training feature data and N categories of support task training feature data; training the target task model based on the target task training feature data and obtaining a first loss of the target task model, and separately training respectively corresponding support task models based on the N categories of support task training feature data and obtaining respective second losses of the N support task models; and updating the memory model, the target task model, and the N support task models based on the first loss and the respective second losses of the N support task models.

Machine learning model training method and apparatus

An image classification method and apparatus, and an image classification model training method and apparatus are provided, which are related to an image recognition technology in the artificial intelligence field and more specifically, to the computer vision field. The method includes: obtaining a to-be-processed image; and classifying the to-be-processed image based on a preset global class feature, to obtain a classification result of the to-be-processed image. The preset global class feature includes a plurality of class features obtained through training based on a plurality of training images in a training set. The plurality of class features in the preset global class feature are used to indicate visual features of all classes in the training set.

Image classification method and apparatus, and image classification model training method and apparatus

The method includes: obtaining a plurality of pieces of feature data; automatically performing two different types of nonlinear combination processing operations on the plurality of pieces of feature data to obtain two groups of processed data, where the two groups of processed data include a group of higher-order data and a group of lower-order data, the higher-order data is related to a nonlinear combination of m pieces of feature data in the plurality of pieces of feature data, and the lower-order data is related to a nonlinear combination of n pieces of feature data in the plurality of pieces of feature data, where m&#x2265;3, and m&#x3e;n&#x2265;2; and determining prediction data based on a plurality of pieces of target data, where the plurality of pieces of target data include the two groups of processed data.

Method for data processing by performing different non-linear combination processing

Example prediction methods and apparatus are described. One example includes sending a first model parameter and a second model parameter by a server to a plurality of terminals. The first model parameter and the second model parameter are adapted to a prediction model of the terminal. The server receives a first prediction loss sent by at least one of the plurality of terminals. A first prediction loss sent by each of the at least one terminal is calculated by the terminal based on the prediction model that uses the first model parameter and the second model parameter. The server updates the first model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated first model parameter. The server updates the second model parameter based on the first prediction loss sent by the at least one terminal to obtain an updated second model parameter.

Prediction method, terminal, and server

Method and apparatus of data processing using multiple types of non-linear combination processing

The method of the present disclosure includes: after a graph partitioning apparatus extracts an edge, first determining whether an aggregation degree between a currently extracted edge and an allocated edge in a first device satisfies a preset condition; then, when the preset condition is satisfied, determining whether a quantity of allocated edges stored in the first device is less than a first preset threshold; and allocating the currently extracted edge to the first device when the quantity is less than the first preset threshold. In this way, an aggregation degree between allocated edges in each device is relatively high and each device has relatively balanced load. When an edge changes and an edge associated with the particular edge needs to be synchronized, a relatively small quantity of devices need to perform synchronization and update, so that costs of communication between devices are reduced, and distributed graph computing efficiency is improved.

Graph partitioning method and apparatus

A data processing method, includes receiving a data flow; generating a triplet set according to the data flow, where each triplet in the set includes three items, the first item is a first element in the data flow, the second item includes a first time point at which the first element appears in the data flow and a first quantity of times that corresponds to the first time point, and the third item includes a second time point at which the first element appears in the data flow and a second quantity of times that corresponds to the second time point; and performing data processing on the data flow according to the triplet set. In the embodiments of the present application, the triplet set may be generated based on the data flow.

Growing community of inventors

Hong Kong, China

Zhenguo Li