公开(公告)号：US20230206668A1

公开(公告)日：2023-06-29

申请号：US18170902

申请日：2023-02-17

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

Inventor： Ruoyu GUO ,  Yuning DU ,  Chenxia LI ,  Qiwen LIU ,  Baohua LAI ,  Yanjun MA ,  Dianhai YU

IPC: G06V30/19 ,  G06V30/18 ,  G06V30/16

CPC classification number: G06V30/19147 ,  G06V30/19173 ,  G06V30/18 ,  G06V30/16

Abstract: The present disclosure provides a vision processing and model training method, device, storage medium and program product. A specific implementation solution is as follows: establishing an image classification network with the same backbone network as the vision model, performing a self-monitoring training on the image classification network by using an unlabeled first data set; initializing a weight of a backbone network of the vision model according to a weight of a backbone network of the trained image classification network to obtain a pre-training model, the structure of the pre-training model being consistent with that of the vision model, and optimize the weight of the backbone network by using real data set in a current computer vision task scenario, so as to be more suitable for the current computer vision task; then, training the pre-training model by using a labeled second data set to obtain a trained vision model.

公开(公告)号：US20240070454A1

公开(公告)日：2024-02-29

申请号：US18108956

申请日：2023-02-13

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

Inventor： Ruoyu GUO ,  Yuning DU ,  Chenxia LI ,  Baohua LAI ,  Yanjun MA

IPC: G06N3/08 ,  G06V10/82

CPC classification number: G06N3/08 ,  G06V10/82

Abstract: Provided is a lightweight model training method, an image processing method, a device and a medium. The lightweight model training method includes: acquiring first and second augmentation probabilities and a target weight adopted in an e-th iteration; performing data augmentation on a data set based on the first and second augmentation probabilities respectively, to obtain first and second data sets; obtaining a first output value of a student model and a second output value of a teacher model based on the first data set; obtaining a third output value and a fourth output value based on the second data set; determining a distillation loss function, a truth-value loss function and a target loss function; training the student model based on the target loss function; and determining a first augmentation probability or target weight to be adopted in an (e+1)-th iteration in a case of e is less than E.

公开(公告)号：US20220343662A1

公开(公告)日：2022-10-27

申请号：US17861741

申请日：2022-07-11

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

Inventor： Yuning DU ,  Yehua YANG ,  Chenxia LI ,  Qiwen LIU ,  Xiaoguang HU ,  Dianhai YU ,  Yanjun MA ,  Ran BI

IPC: G06V30/14 ,  G06V10/82 ,  G06V30/19

Abstract: The present disclosure provides a method and apparatus for recognizing a text, a device and a storage medium, and relates to the field of deep learning technology. A specific implementation comprises: receiving a target image; performing a text detection on the target image using a pre-trained lightweight text detection network, to obtain a text detection box; and recognizing a text in the text detection box using a pre-trained lightweight text recognition network, to obtain a text recognition result.

公开(公告)号：US20220129731A1

公开(公告)日：2022-04-28

申请号：US17568296

申请日：2022-01-04

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

Inventor： Ruoyu GUO ,  Yuning DU ,  Chenxia LI ,  Tingquan GAO ,  Qiao ZHAO ,  Qiwen LIU ,  Ran BI ,  Xiaoguang Hu ,  Dianhai YU ,  Yanjun MA

IPC: G06N3/04 ,  G06N3/08

Abstract: The present disclosure provides a method and apparatus for training an image recognition model, and a method and apparatus for recognizing an image, and relates to the field of artificial intelligence, and particularly to the fields of deep learning and computer vision. A specific implementation comprises: acquiring a tagged sample set, an untagged sample set and a knowledge distillation network; and performing following training steps: selecting an input sample from the tagged sample set and the untagged sample set, and accumulating a number of iterations; inputting respectively the input sample into a student network and a teacher network of the knowledge distillation network to train the student network and the teacher network; and selecting an image recognition model from the student network and the teacher network, if a training completion condition is satisfied.