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：US20250148761A1

公开(公告)日：2025-05-08

申请号：US18717894

申请日：2022-03-03

Applicant: Intel Corporation

Inventor： Dongqi CAI ,  Anbang YAO ,  Chao LI ,  Shandong WANG ,  Yurong CHEN

IPC: G06V10/771 ,  G06T5/20 ,  G06V10/40 ,  G06V20/64

Abstract: The disclosure provides an apparatus, method, device and medium for 3D dynamic sparse convolution. The method includes: receiving an input feature map of a 3D data sample; performing input feature map partition to divide the input feature map into a plurality of disjoint input feature map groups; performing a shared 3D dynamic sparse convolution to the plurality of disjoint input feature map groups respectively to obtain a plurality of output feature maps corresponding to the plurality of disjoint input feature map groups, wherein the shared 3D dynamic sparse convolution comprises a shared 3D dynamic sparse convolutional kernel; and performing output feature map grouping to sequentially stack the plurality of output feature maps to obtain an output feature map corresponding to the input feature map. (FIG. 2).

公开(公告)号：US20240312196A1

公开(公告)日：2024-09-19

申请号：US18565967

申请日：2021-11-30

Applicant: Intel Corporation

Inventor： Dongqi CAI ,  Anbang YAO ,  Yurong CHEN ,  Chao LI

IPC: G06V10/82 ,  G06N3/0464 ,  G06V20/40

CPC classification number: G06V10/82 ,  G06N3/0464 ,  G06V20/42

Abstract: An apparatus, method, device and medium for dynamic quadruple convolution in a 3-dimensional (3D) convolutional neural network (CNN) are provided. The method includes: a multi-dimensional attention block configured to: receive an input feature map of a video data sample; and dynamically generate convolutional kernel scalars along four dimensions of a 3-dimensional convolution kernel space based on the input feature map, the four dimensions comprising an output channel number, an input channel number, a temporal size and a spatial size; and a convolution block configured to sequentially multiply the generated convolutional kernel scalars with a static 3D convolution kernel in a matrix-vector product way to obtain a dynamic kernel of dynamic quadruple convolution.

公开(公告)号：US20240312055A1

公开(公告)日：2024-09-19

申请号：US18569996

申请日：2021-12-10

Applicant: INTEL CORPORATION

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

IPC: G06T7/73 ,  G06T7/80

CPC classification number: G06T7/74 ,  G06T7/80 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06T2207/30221

Abstract: This disclosure describes systems, methods, and devices related to real-time multi-person three-dimensional pose tracking using a single camera. A method may include receiving, by a device, two-dimensional image data from a camera, the two-dimensional image data representing a first person and a second person; generating, based on the two-dimensional image data, two-dimensional positions of body parts represented by the first person; generating, using a deep neural network, based on the two-dimensional positions, a three-dimensional pose regression of the body parts represented by the first person; identifying, based on the two-dimensional positions and the three-dimensional pose regression, contact between a ground plane and a foot of the first person; generating an absolute three-dimensional position of the contact between the ground plane and the foot of the first person; generating, based on the absolute three-dimensional position, a three-dimensional pose of the body parts represented by the first person.

公开(公告)号：US20240013047A1

公开(公告)日：2024-01-11

申请号：US18252231

申请日：2020-12-24

Applicant: Intel Corporation

Inventor： Dongqi CAI ,  Anbang YAO ,  Yurong CHEN ,  Xiaolong LIU

IPC: G06N3/08

CPC classification number: G06N3/08 ,  G06V10/7715

Abstract: Dynamic conditional pooling for neural network processing is disclosed. An example of a storage medium includes instructions for receiving an input at a convolutional layer of a convolutional neural network (CNN); receiving an input sample at a pooling stage of the convolutional layer; generating a plurality of soft weights based on the input sample; performing conditional aggregation on the input sample utilizing the plurality of soft weights to generate an aggregated value; and performing conditional normalization on the aggregated value to generate an output for the convolutional layer.

公开(公告)号：US20230410496A1

公开(公告)日：2023-12-21

申请号：US18252164

申请日：2020-12-23

Applicant: Intel Corporation

Inventor： Anbang YAO ,  Bo LIU ,  Ming LU ,  Feng CHEN ,  Yurong CHEN

IPC: G06V10/82

CPC classification number: G06V10/82

Abstract: Omni-scale convolution for convolutional neural networks is disclosed. An example of an apparatus includes one or more processors to process data, including processing for a convolutional neural network (CNN); and a memory to store data, including CNN data, wherein processing of input data by the CNN includes implementing omni-scale convolution in one or more convolutional layers of the CNN, implementation of the omni-scale convolution into a convolutional layer of the one or more convolutional layers including at least applying multiple dilation rates in a plurality of kernels of a kernel lattice of the convolutional layer, and applying a cyclic pattern for the multiple dilation rates in the plurality of kernels of the convolutional layer.

公开(公告)号：US20220230268A1

公开(公告)日：2022-07-21

申请号：US17517316

申请日：2021-11-02

Applicant: Intel Corporation

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

IPC: G06T1/20 ,  G06N20/00 ,  G06N3/00 ,  G06N3/04 ,  G06N3/08

Abstract: Described herein are advanced artificial intelligence agents for modeling physical interactions. In one embodiment, an apparatus to provide an active artificial intelligence (AI) agent includes at least one database to store physical interaction data and compute cluster coupled to the at least one database. The compute cluster automatically obtains physical interaction data from a data collection module without manual interaction, stores the physical interaction data in the at least one database, and automatically trains diverse sets of machine learning program units to simulate physical interactions with each individual program unit having a different model based on the applied physical interaction data.

公开(公告)号：US20220147791A1

公开(公告)日：2022-05-12

申请号：US17435657

申请日：2019-06-21

Applicant: Intel Corporation

Inventor： Anbang YAO ,  Jiahui ZHANG ,  Dawei SUN ,  Dian GU ,  Yurong CHEN

IPC: G06N3/04

Abstract: Embodiments are generally directed to sparse 3D convolution acceleration in a convolutional layer of an artificial neural network model. An embodiment of an apparatus includes one or more processors including a graphics processor to process data; and a memory for storage of data, including feature maps. The one or more processors are to provide for sparse 3D convolution acceleration by applying a shared 3D convolutional kernel/filter to an input feature map to produce an output feature map, including increasing sparsity of the input feature map by partitioning it into multiple disjoint input groups; generation of multiple disjoint output groups corresponding to the input groups by performing a convolution calculation represented by the shared 3D convolutional kernel/filter on all feature values associated with active/valid voxels of each input group to produce corresponding feature values within corresponding output groups; and outputting the output feature map by sequentially stacking the output groups.

公开(公告)号：US20200234411A1

公开(公告)日：2020-07-23

申请号：US16474848

申请日：2017-04-07

Applicant: INTEL CORPORATION

Inventor： Lin XU ,  Liu YANG ,  Anbang YAO ,  dongqi CAI ,  Libin WANG ,  Ping HU ,  Shaodong WANG ,  Wenhua CHENG ,  Yiwen GUO ,  Yurong CHEN

IPC: G06T5/00 ,  H04N9/64 ,  H04N9/07 ,  G06N3/08 ,  G06N5/04 ,  G06N20/10 ,  G06F9/50

Abstract: Methods and systems are disclosed using camera devices for deep channel and Convolutional Neural Network (CNN) images and formats. In one example, image values are captured by a color sensor array in an image capturing device or camera. The image values provide color channel data. The captured image values by the color sensor array are input to a CNN having at least one CNN layer. The CNN provides CNN channel data for each layer. The color channel data and CNN channel data is to form a deep channel image that stored in a memory. In another example, image values are captured by sensor array. The captured image values by the sensor array are input a CNN having a first CNN layer. An output is generated at the first CNN layer using the captured image values by the color sensor array. The output of the first CNN layer is stored as a feature map of the captured image.

公开(公告)号：US20200082198A1

公开(公告)日：2020-03-12

申请号：US16609732

申请日：2018-05-22

Applicant: INTEL CORPORATION

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

IPC: G06K9/46 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: Methods and apparatus for discriminative 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.