公开(公告)号：US20250068916A1

公开(公告)日：2025-02-27

申请号：US18725028

申请日：2022-02-21

Applicant: Intel Corporation

Inventor： Yurong Chen ,  Anbang Yao ,  Yi Qian ,  Yu Zhang ,  Shandong Wang

IPC: G06N3/088

Abstract: Methods, apparatus, systems, and articles of manufacture are disclosed for teacher-free self-feature distillation training of machine-learning (ML) models. An example apparatus includes at least one memory, instructions, and processor circuitry to at least one of execute or instantiate the instructions to perform a first comparison of (i) a first group of a first set of feature channels (FCs) of an ML model and (ii) a second group of the first set, perform a second comparison of (iii) a first group of a second set of FCs of the ML model and one of (iv) a third group of the first set or a first group of a third set of FCs of the ML model, adjust parameter(s) of the ML model based on the first and/or second comparisons, and, in response to an error value satisfying a threshold, deploy the ML model to execute a workload based on the parameter(s).

公开(公告)号：US12217163B2

公开(公告)日：2025-02-04

申请号：US18371934

申请日：2023-09-22

Applicant: Intel Corporation

Inventor： Yiwen Guo ,  Yuqing Hou ,  Anbang Yao ,  Dongqi Cai ,  Lin Xu ,  Ping Hu ,  Shandong Wang ,  Wenhua Cheng ,  Yurong Chen ,  Libin Wang

IPC: G06K9/62 ,  G06F18/21 ,  G06F18/213 ,  G06F18/214 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063 ,  G06N3/08 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V10/94 ,  G06V20/00

Abstract: Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps. The weighted feature maps are stored in the LSTM. A Q value is calculated for different actions based on the weighted feature maps stored in the LSTM.

公开(公告)号：US12154309B2

公开(公告)日：2024-11-26

申请号：US18462305

申请日：2023-09-06

Applicant: Intel Corporation

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

IPC: G06V10/00 ,  G06F18/243 ,  G06N3/04 ,  G06N3/08 ,  G06V10/44 ,  G06V10/82 ,  G06V20/10 ,  G06V20/70 ,  G06V30/19 ,  G06V30/24

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：US20240086693A1

公开(公告)日：2024-03-14

申请号：US18371934

申请日：2023-09-22

Applicant: Intel Corporation

Inventor： Yiwen GUO ,  Yuqing Hou ,  Anbang YAO ,  Dongqi Cai ,  Lin Xu ,  Ping Hu ,  Shandong Wang ,  Wenhua Cheng ,  Yurong Chen ,  Libin Wang

IPC: G06N3/063 ,  G06F18/21 ,  G06F18/213 ,  G06F18/214 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06V10/44 ,  G06V10/764 ,  G06V10/82 ,  G06V10/94 ,  G06V20/00

CPC classification number: G06N3/063 ,  G06F18/213 ,  G06F18/2148 ,  G06F18/217 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V10/94 ,  G06V10/955 ,  G06V20/00

Abstract: Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps. The weighted feature maps are stored in the LSTM. A Q value is calculated for different actions based on the weighted feature maps stored in the LSTM.

公开(公告)号：US20240013506A1

公开(公告)日：2024-01-11

申请号：US18462305

申请日：2023-09-06

Applicant: Intel Corporation

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

IPC: G06V10/44 ,  G06N3/04 ,  G06N3/08 ,  G06V30/24 ,  G06F18/243 ,  G06V30/19 ,  G06V10/82 ,  G06V20/70 ,  G06V20/10

CPC classification number: G06V10/454 ,  G06N3/04 ,  G06N3/08 ,  G06V30/2504 ,  G06F18/24317 ,  G06V30/19173 ,  G06V10/82 ,  G06V20/70 ,  G06V20/10

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：US11803739B2

公开(公告)日：2023-10-31

申请号：US17584216

申请日：2022-01-25

Applicant: Intel Corporation

Inventor： Yiwen Guo ,  Yuqing Hou ,  Anbang Yao ,  Dongqi Cai ,  Lin Xu ,  Ping Hu ,  Shandong Wang ,  Wenhua Cheng ,  Yurong Chen ,  Libin Wang

IPC: G06K9/62 ,  G06N3/063 ,  G06N3/08 ,  G06V10/94 ,  G06F18/21 ,  G06F18/213 ,  G06F18/214 ,  G06N3/044 ,  G06N3/045 ,  G06V10/764 ,  G06V10/82 ,  G06V10/44 ,  G06V20/00

CPC classification number: G06N3/063 ,  G06F18/213 ,  G06F18/217 ,  G06F18/2148 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V10/94 ,  G06V10/955 ,  G06V20/00

Abstract: Methods and systems for budgeted and simplified training of deep neural networks (DNNs) are disclosed. In one example, a trainer is to train a DNN using a plurality of training sub-images derived from a down-sampled training image. A tester is to test the trained DNN using a plurality of testing sub-images derived from a down-sampled testing image. In another example, in a recurrent deep Q-network (RDQN) having a local attention mechanism located between a convolutional neural network (CNN) and a long-short time memory (LSTM), a plurality of feature maps are generated by the CNN from an input image. Hard-attention is applied by the local attention mechanism to the generated plurality of feature maps by selecting a subset of the generated feature maps. Soft attention is applied by the local attention mechanism to the selected subset of generated feature maps by providing weights to the selected subset of generated feature maps in obtaining weighted feature maps. The weighted feature maps are stored in the LSTM. A Q value is calculated for different actions based on the weighted feature maps stored in the LSTM.

公开(公告)号：US11790644B2

公开(公告)日：2023-10-17

申请号：US17569725

申请日：2022-01-06

Applicant: INTEL CORPORATION

Inventor： Yurong Chen ,  Jianguo Li ,  Zhou Su ,  Zhiqiang Shen

IPC: G06V10/00 ,  G06V10/82 ,  G06F40/169 ,  G06N3/08 ,  G06V20/40 ,  G06F18/214 ,  G06V30/19 ,  G06V30/194 ,  G06V20/70 ,  G06V20/10

CPC classification number: G06V10/82 ,  G06F18/2155 ,  G06F40/169 ,  G06N3/08 ,  G06V20/10 ,  G06V20/41 ,  G06V20/46 ,  G06V20/47 ,  G06V20/70 ,  G06V30/194 ,  G06V30/19173

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.

公开(公告)号：US20230290134A1

公开(公告)日：2023-09-14

申请号：US18019450

申请日：2020-09-25

Applicant: Intel Corporation

Inventor： Ping Hu ,  Anbang Yao ,  Xiaolong Liu ,  Yurong Chen ,  Dongqi Cai

IPC: G06V10/82 ,  G06N3/0464 ,  G06V40/16 ,  G06V10/77

CPC classification number: G06V10/82 ,  G06N3/0464 ,  G06V40/171 ,  G06V10/7715

Abstract: A method and system of multiple facial attributes recognition using highly efficient neural networks.

公开(公告)号：US11568682B2

公开(公告)日：2023-01-31

申请号：US17108256

申请日：2020-12-01

Applicant: INTEL CORPORATION

Inventor： Shaopeng Tang ,  Anbang Yao ,  Yurong Chen

IPC: G06V40/20 ,  G06K9/62 ,  G06T7/215 ,  G06V10/50 ,  G06V20/52 ,  G06V20/64 ,  G06T7/579 ,  G06T7/593

Abstract: Techniques are provided for recognition of activity in a sequence of video image frames that include depth information. A methodology embodying the techniques includes segmenting each of the received image frames into a multiple windows and generating spatio-temporal image cells from groupings of windows from a selected sub-sequence of the frames. The method also includes calculating a four dimensional (4D) optical flow vector for each of the pixels of each of the image cells and calculating a three dimensional (3D) angular representation from each of the optical flow vectors. The method further includes generating a classification feature for each of the image cells based on a histogram of the 3D angular representations of the pixels in that image cell. The classification features are then provided to a recognition classifier configured to recognize the type of activity depicted in the video sequence, based on the generated classification features.

公开(公告)号：US11538164B2

公开(公告)日：2022-12-27

申请号：US17124064

申请日：2020-12-16

Applicant: Intel Corporation

Inventor： Libin Wang ,  Anbang Yao ,  Yurong Chen

IPC: G06V10/00 ,  G06T7/10 ,  G06N3/04 ,  G06N3/08 ,  G06T7/11 ,  G06T7/143 ,  G06V10/26 ,  G06V10/94 ,  G06V10/44 ,  G06F16/55 ,  G06N5/04

Abstract: Techniques related to implementing fully convolutional networks for semantic image segmentation are discussed. Such techniques may include combining feature maps from multiple stages of a multi-stage fully convolutional network to generate a hyper-feature corresponding to an input image, up-sampling the hyper-feature and summing it with a feature map of a previous stage to provide a final set of features, and classifying the final set of features to provide semantic image segmentation of the input image.