公开(公告)号：US12112112B2

公开(公告)日：2024-10-08

申请号：US17095937

申请日：2020-11-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Niv Zehngut ,  Amir Ben-Dror ,  Evgeny Artyomov ,  Michael Dinerstein ,  Roy Jevnisek

IPC: G06F30/39 ,  G06F117/04 ,  G06F117/08 ,  G06F119/06 ,  G06N3/04 ,  G06N3/082 ,  G06N3/086

CPC classification number: G06F30/39 ,  G06N3/04 ,  G06N3/082 ,  G06N3/086 ,  G06F2117/04 ,  G06F2117/08 ,  G06F2119/06

Abstract: Methods, systems, and apparatus for combined or separate implementation of coarse-to-fine neural architecture search (NAS), two-phase block NAS, variable hardware prediction, and differential hardware design are provided and described. A variable predictor is trained, as described herein. Then, a controller or policy may be used to iteratively modify a neural network architecture along dimensions formed by neural network architecture parameters. The modification is applied to blocks (e.g., subnetworks) within the neural network architecture. In each iteration, the remainder of the neural network architecture parameters are modified and learned with a differential NAS method. The training process is performed with two-phase block NAS and incorporates a variable hardware predictor to predict power, performance, and area (PPA) parameters. The hardware parameters may be learned as well using the variable hardware predictor.

公开(公告)号：US11574500B2

公开(公告)日：2023-02-07

申请号：US17151339

申请日：2021-01-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Gil Shapira ,  Noga Levy ,  Roy Jevnisek ,  Ishay Goldin

IPC: G06V40/16 ,  G06N3/08 ,  G06K9/62

Abstract: Embodiments of the present disclosure enable and accurate detection of facial landmarks on mobile devices in real-time. An architecture of a facial landmark detection model is provided including one or more of an attention mechanism (e.g., an attention network), a graph convolution model (e.g., a two-dimensional facial geometry graph convolution model), a multiscale coarse-to-fine mechanism, a patch-facial landmark detachment mechanism, and error estimation techniques. The attention mechanism may increase the accuracy of the facial landmark detection model by attending to meaningful patches. The graph convolution network may improve patch feature aggregation by considering the facial landmarks' geometry. The coarse-to-fine mechanism reduces a network convergence to two cycles (e.g., two facial landmark detection iterations). A patch-facial landmark detachment mechanism reduces the computation burden without significant accuracy degradation. Error estimation techniques provide accurate estimation of the regression error to the computation load and increase the accuracy of the model.

公开(公告)号：US20220075994A1

公开(公告)日：2022-03-10

申请号：US17151339

申请日：2021-01-18

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： GIL SHAPIRA ,  Noga Levy ,  Roy Jevnisek ,  Ishay Goldin

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/08

Abstract: Embodiments of the present disclosure enable and accurate detection of facial landmarks on mobile devices in real-time. An architecture of a facial landmark detection model is provided including one or more of an attention mechanism (e.g., an attention network), a graph convolution model (e.g., a two-dimensional facial geometry graph convolution model), a multiscale coarse-to-fine mechanism, a patch-facial landmark detachment mechanism, and error estimation techniques. The attention mechanism may increase the accuracy of the facial landmark detection model by attending to meaningful patches. The graph convolution network may improve patch feature aggregation by considering the facial landmarks' geometry. The coarse-to-fine mechanism reduces a network convergence to two cycles (e.g., two facial landmark detection iterations). A patch-facial landmark detachment mechanism reduces the computation burden without significant accuracy degradation. Error estimation techniques provide accurate estimation of the regression error to the computation load and increase the accuracy of the model.