公开(公告)号：US20230215148A1

公开(公告)日：2023-07-06

申请号：US18183590

申请日：2023-03-14

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Shuilong DONG ,  Sensen HE ,  Shengyu WEI ,  Cheng CUI ,  Yuning DU ,  Tingquan GAO ,  Shao ZENG ,  Ying ZHOU ,  Xueying LYU ,  Yi LIU ,  Qiao ZHAO ,  Qiwen LIU ,  Ran BI ,  Xiaoguang HU ,  Dianhai YU ,  Yanjun MA

IPC: G06V10/774 ,  G06V10/40 ,  G06V10/74 ,  G06V10/764 ,  G06V10/776 ,  G06V10/778

CPC classification number: G06V10/774 ,  G06V10/40 ,  G06V10/761 ,  G06V10/764 ,  G06V10/776 ,  G06V10/7784

Abstract: The present disclosure provides a method for training a feature extraction model, a method for classifying an image and related apparatuses, and relates to the field of artificial intelligence technology such as deep learning and image recognition. The scheme comprises: extracting an image feature of each sample image in a sample image set using a basic feature extraction module of an initial feature extraction model, to obtain an initial feature vector set; performing normalization processing on each initial feature vector in the initial feature vector set using a normalization processing module of the initial feature extraction model, to obtain each normalized feature vector; and guiding training for the initial feature extraction model through a preset high discriminative loss function, to obtain a target feature extraction model as a training result.

公开(公告)号：US20210374490A1

公开(公告)日：2021-12-02

申请号：US17400693

申请日：2021-08-12

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Yuning DU ,  Yehua YANG ,  Shengyu WEI ,  Ruoyu GUO ,  Qiwen LIU ,  Qiao ZHAO ,  Ran BI ,  Xiaoguang HU ,  Dianhai YU ,  Yanjun MA

IPC: G06K9/68 ,  G06T5/50 ,  G06T7/194 ,  G06N20/00 ,  G06K9/20

Abstract: The present disclosure provides a method and apparatus of processing an image, a device and a medium, which relates to a field of artificial intelligence, and in particular to a field of deep learning and image processing. The method includes: determining a background image of the image, wherein the background image describes a background relative to characters in the image; determining a property of characters corresponding to a selected character section of the image; replacing the selected character section with a corresponding section in the background image, so as to obtain an adjusted image; and combining acquired target characters with the adjusted image based on the property.

公开(公告)号：US20230164446A1

公开(公告)日：2023-05-25

申请号：US17885035

申请日：2022-08-10

Applicant: BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

Inventor： Shengyu WEI ,  Yuning DU ,  Cheng CUI ,  Ruoyu GUO ,  Shuilong DONG ,  Bin LU ,  Tingquan GAO ,  Qiwen LIU ,  Xiaoguang HU ,  Dianhai YU ,  Yanjun MA

IPC: H04N5/235 ,  G06T7/11 ,  G06T7/80 ,  G02F1/133

CPC classification number: H04N5/2353 ,  G06T7/11 ,  G06T7/80 ,  G02F1/13306 ,  G06T2207/20081

Abstract: An imaging exposure control method and apparatus, a device and a storage medium, which relate to the field of artificial intelligence technologies, such as machine learning technologies and intelligent imaging technologies, are disclosed. An implementation includes performing semantic segmentation on a preformed image to obtain semantic segmentation images of at least two semantic regions; estimating an exposure duration of each semantic region based on the semantic segmentation image and the preformed image; and controlling exposure of each semantic region during imaging based on the exposure duration of each semantic region.

公开(公告)号：US20230186599A1

公开(公告)日：2023-06-15

申请号：US18078635

申请日：2022-12-09

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Ruoyu GUO ,  Yuning DU ,  Shengyu WEI ,  Shuilong DONG ,  Qiwen LIU ,  Qiao ZHAO ,  Ran BI ,  Xiaoguang HU ,  Dianhai YU ,  Yanjun MA

IPC: G06V10/74 ,  G06V10/75

CPC classification number: G06V10/761 ,  G06V10/751

Abstract: Provided are an image processing method and apparatus, a device, a medium and a program product. The image processing method includes: performing image augmentation on an original image to obtain at least one augmented image; performing subject detection on the original image and the at least one augmented image to obtain an original detection frame in the original image and an augmented detection frame in the at least one augmented image; determining whether the original detection frame and the augmented detection frame belong to the same subject; and in response to the original detection frame and the augmented detection frame belonging to the same subject, determining a target subject frame in the original image according to the augmented detection frame.

公开(公告)号：US20220247626A1

公开(公告)日：2022-08-04

申请号：US17718149

申请日：2022-04-11

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Cheng CUI ,  Tingquan GAO ,  Shengyu WEI ,  Yuning DU ,  Ruoyu GUO ,  Bin LU ,  Ying ZHOU ,  Xueying LYU ,  Qiwen LIU ,  Xiaoguang HU ,  Dianhai YU ,  Yanjun MA

IPC: H04L41/0806 ,  H04L41/084 ,  H04L41/0894 ,  G06K9/62

Abstract: The present disclosure provides a method for generating a backbone network, an apparatus for generating a backbone network, a device, and a storage medium. The method includes: acquiring a set of a training image, a set of an inference image, and a set of an initial backbone network; training and inferring, for each initial backbone network in the set of the initial backbone network, the initial backbone network by using the set of the training image and the set of the inference image, to obtain an inference time and an inference accuracy of a trained backbone network in an inference process; determining a basic backbone network based on the inference time and the inference accuracy of the trained backbone network in the inference process; and obtaining a target backbone network based on the basic backbone network and a preset target network.