公开(公告)号：US20230168894A1

公开(公告)日：2023-06-01

申请号：US17968943

申请日：2022-10-19

Applicant: Intel Corporation

Inventor： Jianguo Li ,  Yurong Chen

IPC: G06F9/30 ,  G06N3/063 ,  G06N3/044 ,  G06N3/045

CPC classification number: G06F9/30196 ,  G06F9/3016 ,  G06F9/30032 ,  G06F9/30036 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063

Abstract: One embodiment provides for a graphics processor comprising a cache memory and a graphics core coupled with the cache memory. The graphics core includes circuitry configured to generate an approximate weight matrix including a set of one-hot coded weights, perform a forward compute pass with mini batch samples to compute a loss function, perform a backward compute pass to compute a gradient update via stochastic gradient descent according to a loss update, and update the approximate weight matrix based on the gradient update to generate an updated weight matrix.

公开(公告)号：US20230154092A1

公开(公告)日：2023-05-18

申请号：US17914314

申请日：2020-04-23

Applicant: Intel Corporation

Inventor： Shandong Wang ,  Yangyuxuan Kang ,  Anbang Yao ,  Ming Lu ,  Yurong Chen

IPC: G06T13/40 ,  G06T7/70

CPC classification number: G06T13/40 ,  G06T7/70 ,  G06T2207/30196 ,  G06T2207/10024 ,  G06T2207/20084

Abstract: Techniques are disclosed for providing improved pose tracking of a subject using a 2D camera and generating a 3D image that recreates the pose of the subject. A 3D skeleton map is estimated from a 2D skeleton map of the subject using, for example, a neural network. A template 3D skeleton map is accessed or generated having bone segments that have lengths set using, for instance, anthropometry statistics based on a given height of the template 3D skeleton map. An improved 3D skeleton map is then produced by at least retargeting one or more of the plurality of bone segments of the estimated 3D skeleton map to more closely match the corresponding template bone segments of the template 3D skeleton map. The improved 3D skeleton map can then be animated in various ways (e.g., using various skins or graphics) to track corresponding movements of the subject.

公开(公告)号：US11640526B2

公开(公告)日：2023-05-02

申请号：US16609735

申请日：2018-05-22

Applicant: INTEL CORPORATION

Inventor： Yiwen Guo ,  Anbang Yao ,  Hao Zhao ,  Ming Lu ,  Yurong Chen

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/082 ,  G06N3/084 ,  G06N5/00

Abstract: Methods and apparatus are disclosed for enhancing a neural network using binary tensor and scale factor pairs. For one example, a method of optimizing a trained convolutional neural network (CNN) includes initializing an approximation residue as a trained weight tensor for the trained CNN. A plurality of binary tensors and scale factor pairs are determined. The approximation residue is updated using the binary tensors and scale factor pairs.

公开(公告)号：US20220207678A1

公开(公告)日：2022-06-30

申请号：US17482998

申请日：2021-09-23

Applicant: Intel Corporation

Inventor： Anbang Yao ,  Ming Lu ,  Yikai Wang ,  Shandong Wang ,  Yurong Chen ,  Sungye Kim ,  Attila Tamas Afra

IPC: G06T5/50 ,  G06K9/00 ,  G06T7/13 ,  G06N3/02

Abstract: The present disclosure provides an apparatus and method of guided neural network model for image processing. An apparatus may comprise a guidance map generator, a synthesis network and an accelerator. The guidance map generator may receive a first image as a content image and a second image as a style image, and generate a first plurality of guidance maps and a second plurality of guidance maps, respectively from the first image and the second image. The synthesis network may synthesize the first plurality of guidance maps and the second plurality of guidance maps to determine guidance information. The accelerator may generate an output image by applying the style of the second image to the first image based on the guidance information.

公开(公告)号：US20220164669A1

公开(公告)日：2022-05-26

申请号：US17442111

申请日：2019-06-05

Applicant: Intel Corporation

Inventor： Anbang Yao ,  Aojun Zhou ,  Dawei Sun ,  Dian Gu ,  Yurong Chen

IPC: G06N3/08 ,  G06N3/04 ,  G06N3/063

Abstract: Systems, methods, apparatuses, and computer program products to receive a plurality of binary weight values for a binary neural network sampled from a policy neural network comprising a posterior distribution conditioned on a theta value. An error of a forward propagation of the binary neural network may be determined based on a training data and the received plurality of binary weight values. A respective gradient value may be computed for the plurality of binary weight values based on a backward propagation of the binary neural network. The theta value for the posterior distribution may be updated using reward values computed based on the gradient values, the plurality of binary weight values, and a scaling factor.

公开(公告)号：US20220114825A1

公开(公告)日：2022-04-14

申请号：US17408094

申请日：2021-08-20

Applicant: Intel Corporation

Inventor： Anbang Yao ,  Yun Ren ,  Hao Zhao ,  Tao Kong ,  Yurong Chen

IPC: G06V30/24 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: An example apparatus for mining multi-scale hard examples includes a convolutional neural network to receive a mini-batch of sample candidates and generate basic feature maps. The apparatus also includes a feature extractor and combiner to generate concatenated feature maps based on the basic feature maps and extract the concatenated feature maps for each of a plurality of received candidate boxes. The apparatus further includes a sample scorer and miner to score the candidate samples with multi-task loss scores and select candidate samples with multi-task loss scores exceeding a threshold score.

公开(公告)号：US11120314B2

公开(公告)日：2021-09-14

申请号：US16491735

申请日：2017-04-07

Applicant: INTEL CORPORATION

Inventor： Anbang Yao ,  Yun Ren ,  Hao Zhao ,  Tao Kong ,  Yurong Chen

IPC: G06K9/68 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: An example apparatus for mining multi-scale hard examples includes a convolutional neural network to receive a mini-batch of sample candidates and generate basic feature maps. The apparatus also includes a feature extractor and combiner to generate concatenated feature maps based on the basic feature maps and extract the concatenated feature maps for each of a plurality of received candidate boxes. The apparatus further includes a sample scorer and miner to score the candidate samples with multi-task loss scores and select candidate samples with multi-task loss scores exceeding a threshold score.

公开(公告)号：US11106896B2

公开(公告)日：2021-08-31

申请号：US16958542

申请日：2018-03-26

Applicant: INTEL CORPORATION

Inventor： Ping Hu ,  Anbang Yao ,  Yurong Chen ,  Dongqi Cai ,  Shandong Wang

IPC: G06F3/01 ,  G06K9/00 ,  G06K9/62 ,  G06N3/08

Abstract: Methods and apparatus for multi-task recognition using neural networks are disclosed. An example apparatus includes a filter engine to generate a facial identifier feature map based on image data, the facial identifier feature map to identify a face within the image data. The example apparatus also includes a sibling semantic engine to process the facial identifier feature map to generate an attribute feature map associated with a facial attribute. The example apparatus also includes a task loss engine to calculate a probability factor for the attribute, the probability factor identifying the facial attribute. The example apparatus also includes a report generator to generate a report indicative of a classification of the facial attribute.

公开(公告)号：US20210248459A1

公开(公告)日：2021-08-12

申请号：US16973608

申请日：2018-09-27

Applicant: Intel Corporation

Inventor： Jianguo Li ,  Yurong Chen ,  Zheng Wang

IPC: G06N3/08 ,  G06N3/063

Abstract: Embodiments are directed to a composite binary decomposition network. An embodiment of a computer-readable storage medium includes executable computer program instructions for transforming a pre-trained first neural network into a binary neural network by processing layers of the first neural network in a composite binary decomposition process, where the first neural network having floating point values representing weights of various layers of the first neural network. The composite binary decomposition process includes a composite operation to expand real matrices or tensors into a plurality of binary matrices or tensors, and a decompose operation to decompose one or more binary matrices or tensors of the plurality of binary matrices or tensors into multiple lower rank binary matrices or tensors.

公开(公告)号：US20210004572A1

公开(公告)日：2021-01-07

申请号：US16958542

申请日：2018-03-26

Applicant: INTEL CORPORATION

Inventor： Ping Hu ,  Anbang Yao ,  Yurong Chen ,  Dongqi Cai ,  Shandong Wang

IPC: G06K9/00 ,  G06F3/01 ,  G06N3/08

Abstract: Methods and apparatus for multi-task recognition using neural networks are disclosed. An example apparatus includes a filter engine to generate a facial identifier feature map based on image data, the facial identifier feature map to identify a face within the image data. The example apparatus also includes a sibling semantic engine to process the facial identifier feature map to generate an attribute feature map associated with a facial attribute. The example apparatus also includes a task loss engine to calculate a probability factor for the attribute, the probability factor identifying the facial attribute. The example apparatus also includes a report generator to generate a report indicative of a classification of the facial attribute.