公开(公告)号：US20200293904A1

公开(公告)日：2020-09-17

申请号：US16808408

申请日：2020-03-04

Applicant: CORTICA LTD.

Inventor： Igal Raichelgauz ,  Eli Passov

IPC: G06N3/08 ,  G06N3/04

Abstract: A method that may include training a student ODNN to mimic a teacher ODNN. The training may include calculating a teacher student detection loss that is based on a pre-bounding-box output of the teacher ODNN. The pre-bounding-box output of the teacher ODNN is a function of pre-bounding-box outputs of different ODNNs that belong to the teacher ODNN. The method may also include detecting one or more objects in an image, by feeding the image to the trained student ODNN; outputting by the trained student ODNN a student pre-bounding-box output; and calculating one or more bounding boxes based on the student pre-bounding-box output.

公开(公告)号：US11755920B2

公开(公告)日：2023-09-12

申请号：US16808408

申请日：2020-03-04

Applicant: CORTICA LTD.

Inventor： Igal Raichelgauz ,  Eli Passov

IPC: G06N3/088 ,  G06N3/045 ,  G06N3/048

CPC classification number: G06N3/088 ,  G06N3/045 ,  G06N3/048

Abstract: A method that may include training a student ODNN to mimic a teacher ODNN. The training may include calculating a teacher student detection loss that is based on a pre-bounding-box output of the teacher ODNN. The pre-bounding-box output of the teacher ODNN is a function of pre-bounding-box outputs of different ODNNs that belong to the teacher ODNN. The method may also include detecting one or more objects in an image, by feeding the image to the trained student ODNN; outputting by the trained student ODNN a student pre-bounding-box output; and calculating one or more bounding boxes based on the student pre-bounding-box output.

公开(公告)号：US11694088B2

公开(公告)日：2023-07-04

申请号：US16782087

申请日：2020-02-05

Applicant: Cortica Ltd.

Inventor： Igal Raichelgauz ,  Eli Passov

IPC: G06N3/08 ,  G06N3/088 ,  G06N3/045 ,  G06N3/048

CPC classification number: G06N3/088 ,  G06N3/045 ,  G06N3/048

Abstract: A method that may include training a student ODNN to mimic a teacher ODNN. The training may include calculating a teacher student detection loss that is based on a pre-bounding-box output of the teacher ODNN. The pre-bounding-box output of the teacher ODNN is a function of pre-bounding-box outputs of different ODNNs that belong to the teacher ODNN. The method may also include detecting one or more objects in an image, by feeding the image to the trained student ODNN; outputting by the trained student ODNN a student pre-bounding-box output; and calculating one or more bounding boxes based on the student pre-bounding-box output.