公开(公告)号：US20230085732A1

公开(公告)日：2023-03-23

申请号：US18058543

申请日：2022-11-23

申请人： BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

发明人： Yuying HAO ,  Yi LIU ,  Zewu WU ,  Baohua LAI ,  Zeyu CHEN ,  Dianhai YU ,  Yanjun MA ,  Zhiliang YU ,  Xueying LV

IPC分类号： G06T7/11

摘要： The present disclosure provides an image processing method and apparatus, and relates to the field of image processing, and in particular to the field of image annotation. An implementation is: obtaining an image to be processed including a target region to be annotated; in response to a first click on the target region, performing a first operation to expand a predicted region for the target region based on a click position of the first click; in response to a second click in a position where the predicted region exceeds the target region, performing a second operation to reduce the predicted region based on a click position of the second click; and in response to determining that a difference between the predicted region and the target region meets a preset condition, obtaining an outline of the predicted region to annotate the target region.

公开(公告)号：US20240070454A1

公开(公告)日：2024-02-29

申请号：US18108956

申请日：2023-02-13

申请人： Beijing Baidu Netcom Science Technology Co., Ltd.

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

IPC分类号： G06N3/08 ,  G06V10/82

CPC分类号： G06N3/08 ,  G06V10/82

摘要： 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：US20230206668A1

公开(公告)日：2023-06-29

申请号：US18170902

申请日：2023-02-17

申请人： BEIJING BAIDU NETCOM SCIENCE TECHNOLOGY CO., LTD.

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

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

CPC分类号： G06V30/19147 ,  G06V30/19173 ,  G06V30/18 ,  G06V30/16

摘要： 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.