Chinese Academy of Sciences

Huawei Technologies Co., Limited

Zhenan Sun

Qi Cheng Li

Yong He

Yunlong Wang

Kunbo Zhang

Zhengquan Luo

Hui Zhang

Xiaobo Zhang

Bing Yu

Xiang Wu

Wanli Ouyang

Jie Cao

Tieniu Tan

Bailan Feng

Ran He

Yuhao Zhu

Qiang Rao

Yibo Hu

Hongwen Zhang

Disclosed is a disentangled personalized federated learning method via consensus representation extraction and diversity propagation provided by embodiments of the present application. The method includes: receiving, by a current node, local consensus representation extraction models and unique representation extraction models corresponding to other nodes, respectively; extracting, by the current node, the representations of the data of the current node by using the unique representation extraction models of other nodes respectively, and calculating first mutual information between different sets of representation distributions, determining similarity of the data distributions between the nodes based on the size of the first mutual information, and determining aggregation weights corresponding to the other nodes based on the first mutual information; the current node obtains the global consensus representation aggregation model corresponding to the current node.

Disentangled personalized federated learning method via consensus representation extraction and diversity propagation

Disclosed is a method for updating a node model that resists discrimination propagation in federated learning. The method includes: obtaining a node model corresponding to a data node; calculating a mean value of the distribution of class features and a quantity ratio corresponding to training data of the data node, calculating a distribution weighted aggregation model based on the node model, the mean value of the distribution of class features and the quantity ratio; calculating a regularization term corresponding to the data node based on the node model and the distribution weighted aggregation model; calculating a variance of the distribution of the class features corresponding to the data node, calculating a class balanced complementary term by using a cross-domain feature generator; and updating the node model based on the distribution weighted aggregation model, the regularization term, and the class balanced complementary term.

Method for updating a node model that resists discrimination propagation in federated learning

A video generation method includes: obtaining a target face image and a source face image; extracting a feature of each of the source face image and the target face image through a face feature encoder, to obtain corresponding source feature codes and target feature codes; generating swapped face feature codes through a face feature exchanger according to the source feature codes and the target feature codes; generating an initial swapped face image through a face generator according to the swapped face feature codes; and fusing the initial swapped face image with the target face image through a face fuser, to obtain a final swapped face image. The face feature encoder performs hierarchical encoding on the face feature to reserve semantic details of a face, and the face feature exchanger performs further processing based on the hierarchical encoding, to obtain hierarchical encoding of a swapped face feature with semantic details.

Video generation method and system for high resolution face swapping

A reconstruction method of a three-dimensional (3D) human body model includes: acquiring, by a fully convolutional network (FCN) module, a global UVI map and a local UVI map of a body part according to a human body image (S); estimating, by a first neural network, a camera parameter and a shape parameter of the human body model based on the global UVI map (S); extracting, by a second neural network, rotation features of joints of a human body based on the local UVI map (S); refining, by using a position-aided feature refinement strategy, the rotation features of the joints of the human body to acquire refined rotation features (S); and estimating, by a third neural network, a pose parameter of the human body model based on the refined rotation features (S). The reconstruction method achieves accurate and efficient reconstruction of the human body model, and improves robustness of pose estimation.

Reconstruction method of three-dimensional (3D) human body model, storage device and control device

A method and an apparatus for generating a face rotation image are provided. The method includes: performing pose encoding on an obtained face image based on two or more landmarks in the face image, to obtain pose encoded images; obtaining a plurality of training images each including a face from a training data set, wherein presented rotation angles of the faces included in the plurality of training images are the same; performing pose encoding on a target face image based on two or more landmarks in the target face image in the foregoing similar manner, to obtain pose encoded images, wherein the target face image is obtained based on the plurality of training images; generating a to-be-input signal based on the face image and the foregoing two types of pose encoded images; and inputting the to-be-input signal into an face rotation image generative model to obtain a face rotation image.

Method and apparatus for generating face rotation image

A method for identity recognition based on multiple feature fusion for an eye image, which comprises steps of registering and recognizing, wherein the step of registering comprises: obtaining a normalized eye image and a normalized iris image, for a given registered eye image, and extracting a multimode feature of an eye image of a user to be registered, and storing the obtained multimode feature of the eye image as registration information in a registration database; and the step of recognizing comprises: obtaining a normalized eye image and a normalized iris image, for a given recognized eye image, extracting a multimode feature of an eye image of a user to be recognized, comparing the extracted multimode feature with the multimode feature stored in the database to obtain a matching score, and obtaining a fusion score by fusing matching scores at score level, and performing the multiple feature fusion identity recognition on the eye image by a classifier. The present invention recognizes identity by fusing multiple features of eye regions on a human face, and thus achieves high recognition accuracy and is suitable for applications of high security level.

Identity recognition based on multiple feature fusion for an eye image

Growing community of inventors

Beijing, China

Zhenan Sun