公开(公告)号：US20240029397A1

公开(公告)日：2024-01-25

申请号：US18225353

申请日：2023-07-24

Applicant: Beijing University of Posts and Telecommunications

Inventor： Kongming LIANG ,  Zhanyu MA ,  Yurong GUO ,  Ruoyi DU

IPC: G06V10/74 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06V10/761 ,  G06V10/764 ,  G06V10/82

Abstract: The present application discloses a few-shot image recognition method and apparatus, a device, and a storage medium. The method includes: obtaining to-be-recognized images, and constructing an image episode according to the to-be-recognized image, the image episode including a support set and a query set; inputting the image episode into a pre-trained image recognition model, the image recognition model being a few-shot image recognition model based on hard episode training; and calculating a similarity between an image in the query set and each class in the support set according to the image recognition model, and determining the class of to-be-recognized images in the query set according to the similarity. According to the image recognition method provided by the embodiments of the present application, model training and image recognition can be performed by using fewer image samples, and hard episodes are fused into a training process of a few-shot image recognition model, whereby the few-shot image recognition model can be trained more efficiently and quickly, and the trained model is higher in stability and higher in accuracy of image recognition.

公开(公告)号：US20240037918A1

公开(公告)日：2024-02-01

申请号：US18135525

申请日：2023-04-17

Applicant: BEIJING UNIVERSITY OF POSTS AND TELECOMMUNICATIONS

Inventor： Zhanyu MA ,  Kongming LIANG ,  Ruoyi DU ,  Wenqing YU

IPC: G06V10/774 ,  G06V10/764 ,  G06V10/776

CPC classification number: G06V10/774 ,  G06V10/764 ,  G06V10/776

Abstract: A multi-view fine-grained identification method, apparatus, electronic device and medium. By applying the technical scheme of the application, an initial classification model can be trained by using a sample data set consisting of multi-view images of a plurality of multi-view samples. Thus, an efficient fine-grained identification model can be obtained, and this model can actively select the next view image of the same sample for image identification. On the one hand, by aggregating information of multi-view images of the same sample, the limitation of traditional fine-grained image identification methods that only rely on a single picture to provide clues for discrimination is solved. On the other hand, by predicting view images for discrimination, identification efficiency based on multi-view fine-grained identification is improved.

公开(公告)号：US20210133479A1

公开(公告)日：2021-05-06

申请号：US17039346

申请日：2020-09-30

Applicant: Beijing University of Posts and Telecommunications

Inventor： Zhanyu MA ,  Dongliang CHANG ,  Jiyang XIE ,  Yifeng DING ,  Zhongwei SI

IPC: G06K9/46 ,  G06K9/62 ,  G06T7/50 ,  G06N3/04 ,  G06N3/08

Abstract: The present disclosure provides a fine-grained image recognition method, an electronic device and a computer readable storage medium. The method comprises the steps of feature extraction, calculation of feature discriminant loss function, calculation of feature diversity loss function and calculation of model optimization loss function. The present disclosure comprehensively considers influences of factors such as a large intra-class difference, a small inter-class difference, and a great influence of background noise of the fine-grained image, and makes constrains such that the feature maps belonging to each class are discriminative and have the features of corresponding class, thus reducing the intra-class difference, decreasing the learning difficulty and learning better discriminative features. The constraints make the feature maps belonging to each class have a diversity, which increases the inter-class difference, achieves a good result, and is easy for practical deployment, thereby obviously improving the effect of multiple fine-grained image classification tasks.