Invention Grant
- Patent Title: System and method for a unified architecture multi-task deep learning machine for object recognition
-
Application No.: US16808357Application Date: 2020-03-03
-
Publication No.: US11645869B2Publication Date: 2023-05-09
- Inventor: Mostafa El-Khamy , Arvind Yedla , Marcel Nassar , Jungwon Lee
- Applicant: Samsung Electronics Co., Ltd.
- Applicant Address: KR Suwon-si
- Assignee: Samsung Electronics Co., Ltd.
- Current Assignee: Samsung Electronics Co., Ltd.
- Current Assignee Address: KR Suwon-si
- Agency: Renaissance IP Law Group LLP
- Main IPC: G06V40/16
- IPC: G06V40/16 ; G06T7/70

Abstract:
A system to recognize objects in an image includes an object detection network outputs a first hierarchical-calculated feature for a detected object. A face alignment regression network determines a regression loss for alignment parameters based on the first hierarchical-calculated feature. A detection box regression network determines a regression loss for detected boxes based on the first hierarchical-calculated feature. The object detection network further includes a weighted loss generator to generate a weighted loss for the first hierarchical-calculated feature, the regression loss for the alignment parameters and the regression loss of the detected boxes. A backpropagator backpropagates the generated weighted loss. A grouping network forms, based on the first hierarchical-calculated feature, the regression loss for the alignment parameters and the bounding box regression loss, at least one of a box grouping, an alignment parameter grouping, and a non-maximum suppression of the alignment parameters and the detected boxes.
Information query