公开(公告)号：US12112482B2

公开(公告)日：2024-10-08

申请号：US17161139

申请日：2021-01-28

Applicant: Intel Corporation

Inventor： Ke Ding ,  Anthony Rhodes ,  Manan Goel

IPC: G06T7/11 ,  G06N3/045

CPC classification number: G06T7/11 ,  G06N3/045 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Various embodiments are generally directed to techniques for image segmentation utilizing context, such as with a machine learning (ML) model that injects context into various training stages. Many embodiments utilize one or more of an encoder-decoder model topology and select criteria and parameters in hyper-parameter optimization (HPO) to conduct the best model neural architecture search (NAS). Some embodiments are particularly directed to resizing context frames to a resolution that corresponds with a particular stage of decoding. In several embodiments, the context frames are concatenated with one or more of data from a previous decoding stage and data from a corresponding encoding stage prior to being provided as input to a next decoding stage.

公开(公告)号：US20230377341A1

公开(公告)日：2023-11-23

申请号：US18229577

申请日：2023-08-02

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06V20/40 ,  G06T7/168 ,  G06T7/11 ,  G06T11/20 ,  G06F17/18 ,  G06N3/047

CPC classification number: G06V20/49 ,  G06T7/168 ,  G06T7/11 ,  G06T11/20 ,  G06F17/18 ,  G06V20/46 ,  G06N3/047 ,  G06T2207/20081 ,  G06T2210/12 ,  G06T2207/20084

Abstract: Techniques related to automatically segmenting a video frame into fine grain object of interest and background regions using a ground truth segmentation of an object in a previous frame are discussed. Such techniques apply multiple levels of segmentation tracking and prediction based on color, shape, and motion of the segmentation to determine per-pixel object probabilities, and solve an energy summation model to generate a final segmentation for the video frame using the object probabilities.

公开(公告)号：US20220382787A1

公开(公告)日：2022-12-01

申请号：US17816468

申请日：2022-08-01

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Sovan Biswas ,  Giuseppe Raffa

IPC: G06F16/28

Abstract: Systems, apparatuses, and methods include technology that extracts a plurality of features from the input data. The technology generates a confidence metric for the plurality of features. The confidence metric corresponds to a degree that at least one feature of the plurality of features is relevant for classification of the input data. The technology categorizes the input data into a category based on the plurality of features and the confidence metric

公开(公告)号：US11227179B2

公开(公告)日：2022-01-18

申请号：US16586671

申请日：2019-09-27

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06K9/00 ,  G06K9/46 ,  G06N3/08

Abstract: An apparatus, method, system and computer readable medium for video tracking. An exemplar crop is selected to be tracked in an initial frame of a video. Bayesian optimization is applied with each subsequent frame of the video by building a surrogate model of an objective function using Gaussian Process Regression (GPR) based on similarity scores of candidate crops collected from a search space in a current frame of the video. A next candidate crop in the search space is determined using an acquisition function. The next candidate crop is compared to the exemplar crop using a Siamese neural network. Comparisons of new candidate crops to the exemplar crop are made using the Siamese neural network until the exemplar crop has been found in the current frame. The new candidate crops are selected based on an updated surrogate model.

公开(公告)号：US20210150329A1

公开(公告)日：2021-05-20

申请号：US16683326

申请日：2019-11-14

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06N3/08 ,  G06N5/04 ,  G06N20/00 ,  G06T7/10

Abstract: Methods, systems and apparatuses may provide for technology that trains a neural network by inputting video data to the neural network, determining a boundary loss function for the neural network, and selecting weights for the neural network based at least in part on the boundary loss function, wherein the neural network outputs a pixel-level segmentation of one or more objects depicted in the video data. The technology may also operate the neural network by accepting video data and an initial feature set, conducting a tensor decomposition on the initial feature set to obtain a reduced feature set, and outputting a pixel-level segmentation of object(s) depicted in the video data based at least in part on the reduced feature set.

公开(公告)号：US12125212B2

公开(公告)日：2024-10-22

申请号：US17132810

申请日：2020-12-23

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Ke Ding ,  Manan Goel

IPC: G06T7/12 ,  G06T7/33 ,  G06V10/44 ,  G06V10/764

CPC classification number: G06T7/12 ,  G06T7/33 ,  G06V10/454 ,  G06V10/764 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus for high-fidelity vision tasks using deep neural networks are disclosed. An example apparatus includes a feature extractor to extract low-level features and edge-enhanced features of an input image processed using a convolutional neural network, an eidetic memory block generator to generate an eidetic memory block using the extracted low-level features or the extracted edge-enhanced features, and an interactive segmentation network to perform image segmentation using the eidetic memory block, the eidetic memory block used to propagate domain-persistent features through the segmentation network.

公开(公告)号：US20240028876A1

公开(公告)日：2024-01-25

申请号：US18477407

申请日：2023-09-28

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Hong Lu ,  Lama Nachman

IPC: G06N3/047 ,  G06N3/084

CPC classification number: G06N3/047 ,  G06N3/084

Abstract: Example apparatus disclosed include interface circuitry, machine readable instruction, and programmable circuitry to at least one of instantiate or execute the machine readable instructions to access source input data and target input data, identify a domain shift prediction based on at least one of a feature decorrelation of the source input data or a feature decorrelation of the target input data, the domain shift prediction a source domain prediction or a target domain prediction, initiate gradient propagation of a domain loss to determine data features for the domain shift prediction, and rank input data features for the domain shift prediction.

公开(公告)号：US11875254B2

公开(公告)日：2024-01-16

申请号：US16683326

申请日：2019-11-14

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06N3/08 ,  G06N5/046 ,  G06T7/10 ,  G06N20/00 ,  G06V10/44 ,  G06V10/82

CPC classification number: G06N3/08 ,  G06N5/046 ,  G06N20/00 ,  G06T7/10 ,  G06V10/454 ,  G06V10/82 ,  G06T2207/10016 ,  G06T2207/20084

Abstract: Methods, systems and apparatuses may provide for technology that trains a neural network by inputting video data to the neural network, determining a boundary loss function for the neural network, and selecting weights for the neural network based at least in part on the boundary loss function, wherein the neural network outputs a pixel-level segmentation of one or more objects depicted in the video data. The technology may also operate the neural network by accepting video data and an initial feature set, conducting a tensor decomposition on the initial feature set to obtain a reduced feature set, and outputting a pixel-level segmentation of object(s) depicted in the video data based at least in part on the reduced feature set.

公开(公告)号：US11763565B2

公开(公告)日：2023-09-19

申请号：US16678428

申请日：2019-11-08

Applicant: Intel Corporation

Inventor： Anthony Rhodes ,  Manan Goel

IPC: G06K9/00 ,  G06V20/40 ,  G06T7/168 ,  G06T7/11 ,  G06T11/20 ,  G06F17/18 ,  G06N3/047

CPC classification number: G06V20/49 ,  G06F17/18 ,  G06N3/047 ,  G06T7/11 ,  G06T7/168 ,  G06T11/20 ,  G06V20/46 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2210/12

Abstract: Techniques related to automatically segmenting a video frame into fine grain object of interest and background regions using a ground truth segmentation of an object in a previous frame are discussed. Such techniques apply multiple levels of segmentation tracking and prediction based on color, shape, and motion of the segmentation to determine per-pixel object probabilities, and solve an energy summation model to generate a final segmentation for the video frame using the object probabilities.

公开(公告)号：US20230136209A1

公开(公告)日：2023-05-04

申请号：US18148138

申请日：2022-12-29

Applicant: Intel Corporation

Inventor： Anthony Rhodes

IPC: G06F18/21 ,  G06N3/044

Abstract: Disclosed is an example solution to analyze uncertainty of an evidential deep learning neural network with dissonance regularization and recurrent priors. An example apparatus includes processor circuitry to at least one of instantiate or execute the machine readable instructions to receive a first predicted classification of a first input of an evidential deep learning neural network (EVDL NN), identify a first uncertainty metric associated with the EVDL NN, the first uncertainty metric corresponding to the first input of the EVDL NN, calculate a first dissonance score based on the first uncertainty metric, and when the first dissonance score satisfies a threshold, assign the first predicted classification to the first input.