公开(公告)号：US20230343068A1

公开(公告)日：2023-10-26

申请号：US17918080

申请日：2020-06-15

Applicant: Intel Corporation

Inventor： Anbang YAO ,  Yikai WANG ,  Ming LU ,  Shandong WANG ,  Feng CHEN

IPC: G06V10/764 ,  G06V10/32 ,  G06V10/44 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06V10/764 ,  G06V10/32 ,  G06V10/454 ,  G06V10/774 ,  G06V10/82

Abstract: Techniques related to implementing and training image classification networks are discussed. Such techniques include applying shared convolutional layers to input images regardless of resolution and applying normalization selectively based on the input image resolution. Such techniques further include training using mixed image size parallel training and mixed image size ensemble distillation.

公开(公告)号：US20220129759A1

公开(公告)日：2022-04-28

申请号：US17441622

申请日：2019-06-26

Applicant: Intel Corporation

Inventor： Anbang YAO ,  Aojun ZHOU ,  Dawei SUN ,  Dian GU ,  Yurong CHEN

IPC: G06N3/08 ,  G06T9/00 ,  G06N3/04

Abstract: Apparatuses, methods, and GPUs are disclosed for universal loss-error-aware quantization (ULQ) of a neural network (NN). In one example, an apparatus includes data storage to store data including activation sets and weight sets, and a network processor coupled to the data storage. The network processor is configured to implement the ULQ by constraining a low-precision NN model based on a full-precision NN model, to perform a loss-error-aware activation quantization to quantize activation sets into ultra-low-bit versions with given bit-width values, to optimize the NN with respect to a loss function that is based on the full-precision NN model, and to perform a loss-error-aware weight quantization to quantize weight sets into ultra-low-bit versions.

公开(公告)号：US20210104086A1

公开(公告)日：2021-04-08

申请号：US16971132

申请日：2018-06-14

Applicant: Intel Corporation

Inventor： Shandong WANG ,  Ming LU ,  Anbang YAO ,  Yurong CHEN

IPC: G06T13/40 ,  G06N3/04 ,  G06N3/08 ,  G06K9/00 ,  G06T19/20 ,  G06K9/62

Abstract: Techniques related to capturing 3D faces using image and temporal tracking neural networks and modifying output video using the captured 3D faces are discussed. Such techniques include applying a first neural network to an input vector corresponding to a first video image having a representation of a human face to generate a morphable model parameter vector, applying a second neural network to an input vector corresponding to a first and second temporally subsequent to generate a morphable model parameter delta vector, generating a 3D face model of the human face using the morphable model parameter vector and the morphable model parameter delta vector, and generating output video using the 3D face model.

公开(公告)号：US20200242821A1

公开(公告)日：2020-07-30

申请号：US16644088

申请日：2017-10-03

Applicant: INTEL CORPORATION

Inventor： Wenlong YANG ,  Anbang YAO ,  Avi NAHMIAS

IPC: G06T11/20 ,  G06F16/901 ,  G06F16/957 ,  G06F16/908

Abstract: Techniques are disclosed for analyzing a graph image in a disconnected mode, e.g., when a graph is rendered as .jpeg, .gif, .png, and so on, and identifying a portion of the graph image associated with a plot/curve of interest. The identified portion of the graph image may then be utilized to generate an adjusted image. The adjusted image may therefore dynamically increase visibility of the plot/curve of interest relative to other plots/curves, and thus the present disclosures provides additional graph functionalities without access to the data originally used to generate the graph. The disconnected graph functionalities disclosed herein may be implemented within an Internet browser or other “app” that may present images depicting graphs to a user.

公开(公告)号：US20180039864A1

公开(公告)日：2018-02-08

申请号：US15554208

申请日：2015-04-15

Applicant: Intel Corporation

Inventor： Anbang YAO ,  Lin XU ,  Yurong CHEN

IPC: G06K9/62 ,  G06K9/46

CPC classification number: G06K9/6268 ,  G06K9/00268 ,  G06K9/38 ,  G06K9/4642 ,  G06K9/4652 ,  G06K9/6202

Abstract: Techniques related to performing skin detection in an image are discussed. Such techniques may include generating skin and non-skin models based on a skin dominant region and another region, respectively, of the image and classifying individual pixels of the image via a discriminative skin likelihood function based on the skin model and the non-skin model.

公开(公告)号：US20250045573A1

公开(公告)日：2025-02-06

申请号：US18709267

申请日：2022-03-03

Applicant: Intel Corporation

Inventor： Anbang YAO ,  Yikai WANG ,  Zhaole SUN ,  Yi YANG ,  Feng CHEN ,  Zhuo WANG ,  Shandong WANG ,  Yurong CHEN

IPC: G06N3/0495 ,  G06N3/0464

Abstract: The disclosure relates to decimal-bit network quantization of CNN models. Methods, apparatus, systems, and articles of manufacture for quantizing a CNN model includes, for a convolutional layer of the CNN model: allocating a 1-bit convolutional kernel subset to the convolutional layer, wherein the convolutional layer includes 32-bit or 16-bit floating-point convolutional kernels with a size of K×K and the 1-bit convolutional kernel subset includes 2N 1-bit convolutional kernel candidates with the size of K×K, 1≤N

公开(公告)号：US20240176998A1

公开(公告)日：2024-05-30

申请号：US18431458

申请日：2024-02-02

Applicant: Intel Corporation

Inventor： Anbang YAO ,  Hao ZHAO ,  Ming LU ,  Yiwen GUO ,  Yurong CHEN

IPC: G06N3/063 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V10/94 ,  G06V20/10 ,  G06V20/40 ,  G06V20/70

CPC classification number: G06N3/063 ,  G06F18/214 ,  G06N3/04 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V10/955 ,  G06V20/10 ,  G06V20/41 ,  G06V20/70

Abstract: Methods and apparatus for discrimitive semantic transfer and physics-inspired optimization in deep learning are disclosed. A computation training method for a convolutional neural network (CNN) includes receiving a sequence of training images in the CNN of a first stage to describe objects of a cluttered scene as a semantic segmentation mask. The semantic segmentation mask is received in a semantic segmentation network of a second stage to produce semantic features. Using weights from the first stage as feature extractors and weights from the second stage as classifiers, edges of the cluttered scene are identified using the semantic features.

公开(公告)号：US20240143333A1

公开(公告)日：2024-05-02

申请号：US18384714

申请日：2023-10-27

Applicant: Intel Corporation

Inventor： Liu Yang ,  Anbang YAO

IPC: G06F9/38 ,  G06F15/80 ,  G06N3/08 ,  G06N20/00

CPC classification number: G06F9/3867 ,  G06F9/3893 ,  G06F15/80 ,  G06N3/08 ,  G06N20/00 ,  G06T1/20

Abstract: Methods and systems are disclosed using an execution pipeline on a multi-processor platform for deep learning network execution. In one example, a network workload analyzer receives a workload, analyzes a computation distribution of the workload, and groups the network nodes into groups. A network executor assigns each group to a processing core of the multi-core platform so that the respective processing core handle computation tasks of the received workload for the respective group.

公开(公告)号：US20230386072A1

公开(公告)日：2023-11-30

申请号：US18031564

申请日：2020-12-01

Applicant: Intel Corporation

Inventor： Anbang YAO ,  Yangyuxuan KANG ,  Shandong WANG ,  Ming LU ,  Yurong CHEN ,  Wenjian SHAO ,  Yikai WANG ,  Haojun XU ,  Chao YU ,  Chong WONG

IPC: G06T7/73 ,  G06V40/10

CPC classification number: G06T7/73 ,  G06V40/103 ,  G06T2207/30196 ,  G06T2207/20084 ,  G06V10/82

Abstract: Techniques related to 3D pose estimation from a 2D input image are discussed. Such techniques include incrementally adjusting an initial 3D pose generated by applying a lifting network to a detected 2D pose in the 2D input image by projecting each current 3D pose estimate to a 2D pose projection, applying a residual regressor to features based on the 2D pose projection and the detected 2D pose, and combining a 3D pose increment from the residual regressor to the current 3D pose estimate.

公开(公告)号：US20200242734A1

公开(公告)日：2020-07-30

申请号：US16474927

申请日：2017-04-07

Applicant: INTEL CORPORATION

Inventor： Shandong WANG ,  Yiwen GUO ,  Anbang YAO ,  Dongqi CAI ,  Libin WANG ,  Lin XU ,  Ping HU ,  Wenhua CHENG ,  Yurong CHEN

IPC: G06T3/40 ,  G06T1/20 ,  G06N3/08 ,  G06N3/04 ,  G06N5/04 ,  G06N20/10 ,  G06N20/20 ,  G06K9/62

Abstract: Methods and systems are disclosed using improved Convolutional Neural Networks (CNN) for image processing. In one example, an input image is down-sampled into smaller images with a smaller resolution than the input image. The down-sampled smaller images are processed by a CNN having a last layer with a reduced number of nodes than a last layer of a full CNN used to process the input image at a full resolution. A result is outputted based on the processed down-sampled smaller images by the CNN having a last layer with a reduced number of nodes. In another example, shallow CNN networks are built randomly. The randomly built shallow CNN networks are combined to imitate a trained deep neural network (DNN).