公开(公告)号：US12067081B2

公开(公告)日：2024-08-20

申请号：US17485251

申请日：2021-09-24

Applicant: KWAI INC.

Inventor： Ning Xu ,  Jingjing Liu ,  Jinyu Yang

IPC: G06N3/02 ,  G06F18/21 ,  G06F18/2132 ,  G06F18/214 ,  G06N3/094 ,  G06N3/096 ,  G06V10/44 ,  G06V10/82

CPC classification number: G06F18/2148 ,  G06F18/2132 ,  G06F18/2155 ,  G06F18/2178 ,  G06N3/02 ,  G06N3/094 ,  G06N3/096 ,  G06V10/454 ,  G06V10/82 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A method and an apparatus for training a transferable vision transformer (TVT) for unsupervised domain adaption (UDA) in heterogeneous devices are provided. The method includes that a heterogeneous device including one or more graphic processing units (GPUs) loads multiple patches into the TVT which includes a transferability adaption module (TAM). Furthermore, a patch-level domain discriminator in the TAM assigns weights to the multiple patches and determines one or more transferable patches based on the weights. Moreover, the heterogeneous device generates a transferable attention output for an attention module in the TAM based on the one or more transferable patches.

公开(公告)号：US12061672B2

公开(公告)日：2024-08-13

申请号：US17465716

申请日：2021-09-02

Applicant: CANON KABUSHIKI KAISHA

Inventor： Norihito Hiasa

IPC: G06V10/70 ,  G06F18/2132 ,  G06F18/214 ,  G06N20/00 ,  G06T3/40 ,  G06V10/20

CPC classification number: G06F18/2148 ,  G06F18/2132 ,  G06N20/00 ,  G06T3/40 ,  G06V10/70 ,  G06V10/20

Abstract: A method for processing an image uses a generator which is a machine learning model. The generator converts an input low resolution image into a first feature map. From the first feature map, a first intermediate image and a second intermediate image each having resolution higher than resolution of the low resolution image are generated. Based on the first intermediate image and the second intermediate image, an estimated image having higher resolution than the resolution of the low resolution image is generated.

公开(公告)号：US11989013B2

公开(公告)日：2024-05-21

申请号：US17421521

申请日：2019-01-18

Applicant: NEC Corporation

Inventor： Kosuke Yoshida

IPC: G05B23/02 ,  G06F18/2132 ,  G06N3/04

CPC classification number: G05B23/0221 ,  G06F18/2132 ,  G06N3/04

Abstract: An abnormality detection apparatus (200) includes storage means (210) for storing a learned self-encoder (211) including predetermined number of two or more of elements as input layers, extraction means (220) for extracting a target data group of a predetermined period including data pieces from time series data measured by one or more sensors, the number of the data pieces being the predetermined number, conversion means (230) for converting the target data group into multi-dimensional vector data including the predetermined number of elements, identifying means (240) for identifying a time period in which there may be a cause of an abnormality from the predetermined period based on a difference between output vector data having the predetermined number of elements obtained by inputting the multi-dimensional vector data to the self-encoder (211) and the multi-dimensional vector data, and output means (250) for outputting abnormality detection information including the identified time period.

公开(公告)号：US11983492B2

公开(公告)日：2024-05-14

申请号：US17014256

申请日：2020-09-08

Applicant: BEIJING DIDI INFINITY TECHNOLOGY AND DEVELOPMENT CO., LTD.

Inventor： Kun Han ,  Haiyang Xu

IPC: G06F40/216 ,  G06F18/211 ,  G06F18/2132 ,  G06F18/2431 ,  G06N3/044 ,  G06N20/20 ,  G06N3/045

CPC classification number: G06F40/216 ,  G06F18/211 ,  G06F18/2132 ,  G06F18/2431 ,  G06N3/044 ,  G06N3/045 ,  G06N20/20

Abstract: Embodiments of the disclosure provide a multi-class classification system. An exemplary system includes at least one processor and at least one non-transitory memory storing instructions that, when executed by the at least one processor, cause the system to perform operations. The operation includes applying a multi-class classifier to classify a set of objects into multiple classes and applying a plurality of binary classifiers to the set of objects, wherein the plurality of binary classifiers are decomposed from the multi-class classifier, each binary classifier classifying the set of the objects into a first group consisting of one or more classes selected from the multiple classes and a second group consisting of one or more remaining classes of the multiple classes. The operation also includes jointly classifying the set of objects using the multi-class classifier and the plurality of binary classifiers.

公开(公告)号：US11847245B2

公开(公告)日：2023-12-19

申请号：US17177822

申请日：2021-02-17

Applicant: Capital One Services, LLC

Inventor： Anh Truong ,  Austin Walters ,  Jeremy Goodsitt ,  Vincent Pham ,  Reza Farivar ,  Galen Rafferty

IPC: G06F21/00 ,  G06F21/62 ,  G06N20/00 ,  G06V20/62 ,  G06V30/262 ,  G06F18/2132

CPC classification number: G06F21/6245 ,  G06F18/2132 ,  G06N20/00 ,  G06V20/62 ,  G06V30/274

Abstract: Systems as described herein may label data to preserve privacy. An annotation server may receive a document comprising a collection of text representing a plurality of confidential data from a first computing device. The annotation server may convert the document to a plurality of text embeddings. The annotation server may input the text embeddings into a machine learning model to generate a plurality of synthetic images, and receive a label for each of the plurality of synthetic images from a third-party labeler. Accordingly, the annotation server may send the confidential data and the corresponding labels to a second computing device.

公开(公告)号：US11775617B1

公开(公告)日：2023-10-03

申请号：US17201358

申请日：2021-03-15

Applicant: Amazon Technologies, Inc.

Inventor： Ayush Jaiswal ,  Yue Wu ,  Pradeep Natarajan ,  Premkumar Natarajan

IPC: G06K9/00 ,  G06F18/2413 ,  G06F16/53 ,  G06F40/20 ,  G06V10/40 ,  G06F18/22 ,  G06F18/2132

CPC classification number: G06F18/2413 ,  G06F16/53 ,  G06F18/2132 ,  G06F18/22 ,  G06F40/20 ,  G06V10/40

Abstract: Devices and techniques are generally described for class-agnostic object detection. In some examples, a first frame of image data comprising a first plurality of pixels may be received. First class-agnostic feature data representing the first plurality of pixels may be generated. A first object detection component may be used to determine that the first plurality of pixels corresponds to an arbitrary object represented in the first frame of image data based at least in part on the first class-agnostic feature data. Class-agnostic data indicating that the first plurality of pixels in the first frame of image data corresponds to the arbitrary object may be generated.

公开(公告)号：US11734392B2

公开(公告)日：2023-08-22

申请号：US17237978

申请日：2021-04-22

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Yang Xue ,  Fan Wang ,  Jingzhou He

IPC: G06F18/40 ,  G06T7/246 ,  G06F40/30 ,  G06V20/40 ,  G06F18/25 ,  G06F18/2132

CPC classification number: G06F18/40 ,  G06F18/2132 ,  G06F18/253 ,  G06F40/30 ,  G06T7/251 ,  G06V20/46 ,  G06T2207/20084

Abstract: An active interaction method, an electronic device and a readable storage medium, relating to the field of deep learning and image processing technologies, are disclosed. According to an embodiment, the active interaction method includes: acquiring a video shot in real time; extracting a visual target from each image frame of the video, and generating a first feature vector of each visual target; for each image frame of the video, fusing the first feature vector of each visual target and identification information of the image frame to which the visual target belongs to generate a second feature vector of each visual target; aggregating the second feature vectors with the same identification information respectively to generate a third feature vector corresponding to each image frame; and initiating active interaction in response to determining that the active interaction is to be performed according to the third feature vector of a preset image frame.

公开(公告)号：US12112529B2

公开(公告)日：2024-10-08

申请号：US17230455

申请日：2021-04-14

Applicant: HYUNDAI MOTOR COMPANY ,  KIA CORPORATION

Inventor： Min Woo Kang ,  Soon Woo Kwon ,  Chung An Lee ,  Hyun Ki Kim ,  Seung Hyun Hong ,  Jun Yun Kang

IPC: G06V10/82 ,  G06F18/2132 ,  G06F18/24 ,  G06N3/044 ,  G06N3/045 ,  G06N3/048 ,  G06N3/08 ,  G06N3/082 ,  G06N20/00 ,  G06T3/60 ,  G06T7/00 ,  G06T7/11 ,  G06V20/70

CPC classification number: G06V10/82 ,  G06F18/2132 ,  G06F18/24 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06N3/082 ,  G06T3/60 ,  G06T7/0002 ,  G06T7/0004 ,  G06T7/11 ,  G06V20/70 ,  G06N3/048 ,  G06N20/00 ,  G06T2207/10056 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30136 ,  G06T2207/30168

Abstract: An apparatus and a method for segmenting a steel microstructure phase are provided. The apparatus includes a storage configured for storing a machine learning algorithm and a processing device that segments a microstructure phase using the machine learning algorithm. The processing device is configured to receive label data, to learn a machine learning model by use of the label data as learning data for the machine learning model, and to segment a phase of a steel microstructure image by use of the learned machine learning model.

公开(公告)号：US20240233112A1

公开(公告)日：2024-07-11

申请号：US18260408

申请日：2021-12-29

Applicant: DAYE SPECIAL STEEL CO., LTD.

Inventor： Zhicheng ZHANG ,  Jin KE ,  Wei FANG ,  Shaoyang ZHANG ,  Changyuan ZHANG

IPC: G06T7/00 ,  C23F1/00 ,  G06F18/2132 ,  G06T7/11 ,  G06T7/174 ,  G06V10/75

CPC classification number: G06T7/001 ,  G06F18/2132 ,  G06T7/11 ,  G06T7/174 ,  G06V10/751 ,  C23F1/00 ,  G06T2207/30136

Abstract: A machine vision-based automatic identification and rating method and system for a low-magnification acid etching defect. The method is used for automatically identifying and rating a defect of a low-magnification aid etching sample of an steel material or a steel billet or a continuous casting billet after acid etching, and comprises: according to a first preset condition, performing image acquisition on the low-magnification acid etching sample of the steel material to obtain a first image (S101); performing automatic image processing on the first image to obtain a second image (S102); according to a second preset condition, performing image segmentation on the second image to obtain a third image (S103); according to a pre-known defect type, performing defect mode identification on the third image to obtain the distribution data of defect modes in the low-magnification acid etching sample (S104); obtaining the quantitative data of various defect modes in the low-magnification acid etching sample according to the third image and the distribution data of the defect modes in the low-magnification acid etching sample (S105); and performing rating on the defect in the low-magnification acid etching sample according to the quantitative data of the defect modes in the low-magnification acid etching sample (S106).

公开(公告)号：US11941857B2

公开(公告)日：2024-03-26

申请号：US17324819

申请日：2021-05-19

Applicant: HI LLC

Inventor： Hamid Dehghani ,  Ryan Field ,  Julian Kates-Harbeck ,  Viktoria Rojkova ,  Ashutosh Chaturvedi

IPC: G06V10/14 ,  G02B27/01 ,  G06F18/10 ,  G06F18/2132 ,  G06F18/2135 ,  G06V10/141 ,  G06V10/147 ,  G06V10/50 ,  G06V10/75

CPC classification number: G06V10/141 ,  G02B27/0172 ,  G06F18/10 ,  G06F18/2132 ,  G06F18/2135 ,  G06V10/14 ,  G06V10/147 ,  G06V10/507 ,  G06V10/76 ,  G02B2027/014

Abstract: An illustrative method includes accessing, by a computing device, a model simulating light scattered by a simulated target, the model comprising a plurality of parameters. The method further includes generating, by the computing device, a set of possible histogram data using the model with a plurality of values for the parameters. The method further includes determining, by the computing device, a set of components that represent the set of possible histogram data, the set of components having a reduced dimensionality from the set of possible histogram data.