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：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).

公开(公告)号：US20200027015A1

公开(公告)日：2020-01-23

申请号：US16474515

申请日：2017-04-07

Applicant: INTEL CORPORATION

Inventor： Angang YAO ,  Dongqi CAI ,  Libin WANG ,  Lin XU ,  Ping HU ,  Shandong WANG ,  Wenhua CHENG ,  Yiwen GUO ,  Liu YANG ,  Yurong CHEN ,  Yuqing HOU ,  Zhou SU

IPC: G06N7/00 ,  G06T1/20 ,  G06F9/48 ,  G06N20/00

Abstract: Described herein are systems and methods for providing deeply stacked automated program synthesis. In one embodiment, an apparatus to perform automated program synthesis includes a memory to store instructions for automated program synthesis and a compute cluster coupled to the memory. The compute cluster supports the instructions for performing the automated program synthesis including partitioning sketched data into partitions, training diverse sets of individual program synthesis units each having different capabilities with partitioned sketched data and for each partition applying respective transformations, and generating sketched baseline data for each individual program synthesis unit.

公开(公告)号：US20190197407A1

公开(公告)日：2019-06-27

申请号：US16328182

申请日：2016-09-26

Applicant: INTEL CORPORATION

Inventor： Anbang YAO ,  Yiwen GUO ,  Lin XU ,  Yan LIN ,  Yurong CHEN

IPC: G06N3/08 ,  G06N3/04 ,  G06F17/16

CPC classification number: G06N3/082 ,  G06F17/16 ,  G06N3/02 ,  G06N3/04 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/084

Abstract: An apparatus and method are described for reducing the parameter density of a deep neural network (DNN). A layer-wise pruning module to prune a specified set of parameters from each layer of a reference dense neural network model to generate a second neural network model having a relatively higher sparsity rate than the reference neural network model; a retraining module to retrain the second neural network model in accordance with a set of training data to generate a retrained second neural network model; and the retraining module to output the retrained second neural network model as a fmal neural network model if a target sparsity rate has been reached or to provide the retrained second neural network model to the layer-wise pruning model for additional pruning if the target sparsity rate has not been reached.

公开(公告)号：US20240005628A1

公开(公告)日：2024-01-04

申请号：US18031064

申请日：2020-11-19

Applicant: Intel Corporation

Inventor： Dongqi CAI ,  Anbang YAO ,  Yikai WANG ,  Ming LU ,  Yurong CHEN

IPC: G06V10/44 ,  G06V10/80 ,  G06V10/82

CPC classification number: G06V10/454 ,  G06V10/82 ,  G06V10/811 ,  G06V10/806

Abstract: Techniques related to bidirectional compact deep fusion networks for multimodal image inputs are discussed. Such techniques include applying a shared convolutional layer and independent batch normalization layers to input volumes for each modality and fusing features from the resultant output volumes in both directions across the modalities.

公开(公告)号：US20230359873A1

公开(公告)日：2023-11-09

申请号：US18142997

申请日：2023-05-03

Applicant: Intel Corporation

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

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

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

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：US20210200993A1

公开(公告)日：2021-07-01

申请号：US17058078

申请日：2018-09-13

Applicant: Intel Corporation

Inventor： Yurong CHEN ,  Jianguo LI

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: Techniques related to implementing convolutional neural networks for face or other object recognition are discussed. Such techniques may include applying, in turn, a depth-wise separable convolution, a condense point-wise convolution, and an expansion point-wise convolution to input feature maps to generate output feature maps such that the output from the expansion point-wise convolution has more channels than the output from the condense point-wise convolution.

公开(公告)号：US20210142115A1

公开(公告)日：2021-05-13

申请号：US16616533

申请日：2017-06-29

Applicant: INTEL CORPORATION

Inventor： Yurong CHEN ,  Jianguo LI ,  Zhou SU ,  Zhiqiang SHEN

IPC: G06K9/62 ,  G06K9/00 ,  G06N3/08 ,  G06F40/169

Abstract: Techniques and apparatus for generating dense natural language descriptions for video content are described. In one embodiment, for example, an apparatus may include at least one memory and logic, at least a portion of the logic comprised in hardware coupled to the at least one memory, the logic to receive a source video comprising a plurality of frames, determine a plurality of regions for each of the plurality of frames, generate at least one region-sequence connecting the determined plurality of regions, apply a language model to the at least one region-sequence to generate description information comprising a description of at least a portion of content of the source video. Other embodiments are described and claimed.