公开(公告)号：US20230153380A1

公开(公告)日：2023-05-18

申请号：US17527295

申请日：2021-11-16

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zhixiang CHI ,  Li GU ,  Huan LIU ,  Yuanhao YU ,  Yang WANG ,  Jin TANG

IPC: G06K9/62 ,  G06K9/00 ,  G06N3/04 ,  G06N3/08

CPC classification number: G06K9/6232 ,  G06K9/6262 ,  G06K9/6257 ,  G06K9/6279 ,  G06K9/00979 ,  G06N3/0454 ,  G06N3/08

Abstract: This disclosure provides for methods and system for meta few-shot class incremental learning. According to an aspect a method is provided. The method includes obtaining at least one weight attention map of a first network and updating weights of a second network using the at least one weight attention map, where the second network is a modulatory network. The method further includes generating at least one feature attention map of the second network based on the at least one weight attention map of the first network and a set of input images of at least one class. The method further includes generating at least one feature map of the first network based on the set of input images of the at least one class, and updating the at least one feature map of the first network based on the feature attention map of the second network.

公开(公告)号：US20240046107A1

公开(公告)日：2024-02-08

申请号：US17966568

申请日：2022-10-14

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zhixiang CHI ,  Li GU ,  Tao ZHONG ,  Yuanhao YU ,  Yang WANG ,  Jin TANG

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/088 ,  G06N3/0427

Abstract: A method has the steps of obtaining a set of training samples from one or more domains, using the set of training samples to query a plurality of artificial-intelligence (AI) models, combining the outputs of the queried AI models, and adapting a target AI model via knowledge distillation using the combined outputs.

公开(公告)号：US20230072445A1

公开(公告)日：2023-03-09

申请号：US17468224

申请日：2021-09-07

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Hanwen LIANG ,  Peng DAI ,  Zhixiang CHI ,  Lizhe CHEN ,  Juwei LU

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: This disclosure provides a training method and apparatus, and relates to the artificial intelligence field. The method includes feeding a primary video segment, representative of a concatenation of a first and a second nonadjacent video segments obtained from a video source, to a deep learning backbone network. The method further includes embedding, via the deep learning backbone network, the primary video segment into a first feature output. The method further includes providing the first feature output to a first perception network to generate a first set of probability distribution outputs indicating a temporal location of a discontinuous point associated with the primary video segment. The method further includes generating a first loss function based on the first set of probability distribution outputs. The method further includes optimizing the deep learning backbone network, by backpropagation of the first loss function.