Patents Examined by Juan A. Torres
  • Patent number: 11366987
    Abstract: A computer-implemented method of determining an explainability mask for classification of an input image by a trained neural network. The trained neural network is configured to determine the classification and classification score of the input image by determining a latent representation of the input image at an internal layer of the trained neural network. The method includes accessing the trained neural network, obtaining the input image and the latent representation thereof and initializing a mask for indicating modifications to the latent representation. The mask is updated by iteratively adjusting values of the mask to optimize an objective function, comprising i) a modification component indicating a degree of modifications indicated by the mask, and ii) a classification score component, determined by applying the indicated modifications to the latent representation and determining the classification score thereof. The mask is scaled to a spatial resolution of the input image and output.
    Type: Grant
    Filed: December 29, 2020
    Date of Patent: June 21, 2022
    Assignee: Robert Bosch GmbH
    Inventor: Andres Mauricio Munoz Delgado
  • Patent number: 11367268
    Abstract: Object re-identification refers to a process by which images that contain an object of interest are retrieved from a set of images captured using disparate cameras or in disparate environments. Object re-identification has many useful applications, particularly as it is applied to people (e.g. person tracking). Current re-identification processes rely on convolutional neural networks (CNNs) that learn re-identification for a particular object class from labeled training data specific to a certain domain (e.g. environment), but that do not apply well in other domains. The present disclosure provides cross-domain disentanglement of id-related and id-unrelated factors. In particular, the disentanglement is performed using a labeled image set and an unlabeled image set, respectively captured from different domains but for a same object class.
    Type: Grant
    Filed: August 20, 2020
    Date of Patent: June 21, 2022
    Assignee: NVIDIA CORPORATION
    Inventors: Xiaodong Yang, Yang Zou, Zhiding Yu, Jan Kautz
  • Patent number: 11361569
    Abstract: Techniques are provided for generating and applying a granular attention hierarchical neural network model to classify a document. In various embodiments, data indicative of the document may be obtained (102) and processed (104) into a first layer of two or more layers of a hierarchical network model using a dual granularity attention mechanism to generate first layer output data, wherein the dual granularity attention mechanism weighs some portions of the data indicative of the document more heavily. Some portions of the data indicative of the document are integrated into the hieratical network model during training of the dual granularity attention mechanism. The first layer output data may be processed (106) in the second of two or more layers of the hierarchical network model to generate second layer output data. A classification label can be generated (108) from the second layer output data.
    Type: Grant
    Filed: August 3, 2018
    Date of Patent: June 14, 2022
    Assignee: KONINKLIJKE PHILIPS N.V.
    Inventors: Yuan Ling, Sheikh Sadid Al Hasan, Oladimeji Feyisetan Farri, Junyi Liu
  • Patent number: 11361223
    Abstract: A multi-beam transmission method is provided for transmitting using an N-beam transmitter to a receiver having K receive beams. In the transmitter, a non-linear encoder implemented by a machine learning block, and a linear encoder are trained using gradient descent back propagation that relies on feedback from the receiver. For each input to be transmitted the machine learning block is used to process the input to produce N/K sets of L outputs. The linear encoder is used to perform linear encoding on each set of L outputs to produce a respective set of K outputs so as to produce N/K sets of K encoded outputs overall and N encoded outputs overall. One of the N/K sets of K outputs from each set of K beams.
    Type: Grant
    Filed: July 24, 2020
    Date of Patent: June 14, 2022
    Assignee: HUAWEI TECHNOLOGIES CO., LTD.
    Inventors: Yiqun Ge, Wuxian Shi, Wen Tong
  • Patent number: 11354792
    Abstract: Technologies for image processing based on a creation workflow for creating a type of images are provided. Both multi-stage image generation as well as multi-stage image editing of an existing image are supported. To accomplish this, one system models the sequential creation stages of the creation workflow. In the backward direction, inference networks can backward transform an image into various intermediate stages. In the forward direction, generation networks can forward transform an earlier-stage image into a later-stage image based on stage-specific operations. Advantageously, this technical solution overcomes the limitations of the single-stage generation strategy with a multi-stage framework to model different types of variation at various creation stages. Resultantly, both novices and seasoned artists can use these technologies to efficiently perform complex artwork creation or editing tasks.
    Type: Grant
    Filed: February 7, 2020
    Date of Patent: June 7, 2022
    Assignee: Adobe Inc.
    Inventors: Matthew David Fisher, Hung-Yu Tseng, Yijun Li, Jingwan Lu
  • Patent number: 11347965
    Abstract: The technology disclosed relates to generating ground truth training data to train a neural network-based template generator for cluster metadata determination task. In particular, it relates to accessing sequencing images, obtaining, from a base caller, a base call classifying each subpixel in the sequencing images as one of four bases (A, C, T, and G), generating a cluster map that identifies clusters as disjointed regions of contiguous subpixels which share a substantially matching base call sequence, determining cluster metadata based on the disjointed regions in the cluster map, and using the cluster metadata to generate the ground truth training data for training the neural network-based template generator for the cluster metadata determination task.
    Type: Grant
    Filed: March 20, 2020
    Date of Patent: May 31, 2022
    Assignee: Illumina, Inc.
    Inventors: Anindita Dutta, Dorna Kashefhaghighi, Amirali Kia
  • Patent number: 11341361
    Abstract: An analysis method executed by a computer includes acquiring a refine image that maximizes a score for inferring a correct label by an inferring process using a trained model, the refine image being generated from an input image used when an incorrect label is inferred; generating a map indicating a region of pixels having the same or similar level of attention degree related to inference in the inferring process, of a plurality of pixels in the generated refine image, based on a feature amount used in the inferring process; extracting an image corresponding to a pixel region whose level in the generated map is a predetermined level, from calculated images calculated based on the input image and the refine image; and generating an output image that specifies a portion related to an inference error in the inferring process, among the calculated images, based on image processing on the extracted image.
    Type: Grant
    Filed: October 6, 2020
    Date of Patent: May 24, 2022
    Assignee: FUJITSU LIMITED
    Inventors: Tomonori Kubota, Takanori Nakao, Yasuyuki Murata
  • Patent number: 11341364
    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an action selection neural network that is used to control a robotic agent interacting with a real-world environment.
    Type: Grant
    Filed: September 20, 2018
    Date of Patent: May 24, 2022
    Assignee: Google LLC
    Inventors: Konstantinos Bousmalis, Alexander Irpan, Paul Wohlhart, Yunfei Bai, Mrinal Kalakrishnan, Julian Ibarz, Sergey Vladimir Levine, Kurt Konolige, Vincent O. Vanhoucke, Matthew Laurance Kelcey
  • Patent number: 11334763
    Abstract: An image processing method includes: inputting a to-be-processed image into a neural network; and forming discrete feature data of the to-be-processed image via the neural network, where the neural network is trained based on guidance information, and during the training process, the neural network is taken as a student neural network; the guidance information includes: a difference between discrete feature data formed by a teacher neural network for an image sample and discrete feature data formed by the student neural network for the image sample.
    Type: Grant
    Filed: December 2, 2019
    Date of Patent: May 17, 2022
    Assignee: BEIJING SENSETIME TECHNOLOGY DEVELOPMENT CO., LTD.
    Inventors: Yi Wei, Hongwei Qin
  • Patent number: 11334766
    Abstract: Systems and methods are provided for training object detectors of a neural network model with a mixture of label noise and bounding box noise. According to some embodiments, a learning framework is provided which jointly optimizes object labels, bounding box coordinates, and model parameters by performing alternating noise correction and model training. In some embodiments, to disentangle label noise and bounding box noise, a two-step noise correction method is employed. In some examples, the first step performs class-agnostic bounding box correction by minimizing classifier discrepancy and maximizing region objectness. In some examples, the second step uses dual detection heads for label correction and class-specific bounding box refinement.
    Type: Grant
    Filed: January 31, 2020
    Date of Patent: May 17, 2022
    Assignee: salesforce.com, inc.
    Inventors: Junnan Li, Chu Hong Hoi
  • Patent number: 11335106
    Abstract: An example computer-vision system to convert images includes an image converter (112) to convert a near infrared light first image (202) to form a visible light image (206), and to update a coefficient of the image converter (112) based on a difference (214), an object recognizer (102) to recognize an object (208) in the first visible light image (206), and an object recognition analyzer (210) to determine the difference (214) between the object (208) recognized in the first visible light image (206) and an object (212) associated with the near infrared light image (202).
    Type: Grant
    Filed: November 29, 2017
    Date of Patent: May 17, 2022
    Assignee: INTEL CORPORATION
    Inventors: Tae-Hoon Kim, Minje Park
  • Patent number: 11321586
    Abstract: A method is provided for determining an operating state of a burner. The method includes receiving baseline characteristic data for a plurality of burner operating states. The baseline characteristic data for each burner operating state of the plurality of burner operating states comprises baseline data of a plurality of data types indicative of a corresponding burner operating state. The method also includes receiving monitoring data captured for a burner by a plurality of burner sensors. The method further includes using to machine learning to compare at least a portion of the monitoring data captured for the burner with the baseline characteristic data. The method still further includes determining an operating state of the burner based at least in part on results of comparing the at least a portion of the monitoring data with the baseline characteristic data. A corresponding apparatus and computer program product are also provided.
    Type: Grant
    Filed: September 25, 2019
    Date of Patent: May 3, 2022
    Assignee: HONEYWELL INTERNATIONAL INC.
    Inventors: Mohammad Hadi Fahandezh Saadi, Raghava Balusu, Vijayendra Grampurohit
  • Patent number: 11321587
    Abstract: A system and a method can receive a first dataset having a first label and a first context. The system and the method can also generate, at the trained deep neural network, a second dataset having the first label and a second context according to a mapping, wherein a first mapping of the plurality of mapping comprises one or more weights of the trained deep neural network that maps data having the first label and the first context to data having a second label and the first context and a second mapping of the plurality of mapping comprises one or more weights of the trained deep neural network that maps data having a second label and the first context to data having the second label and the second context, wherein the second context is different from the first context and the second label is different from the first label.
    Type: Grant
    Filed: January 30, 2020
    Date of Patent: May 3, 2022
    Assignee: Ford Global Technologies, LLC
    Inventors: Akhil Perincherry, Christopher Cruise
  • Patent number: 11323177
    Abstract: Various embodiments provide a method for free space optical communication performance prediction method. The method includes: in a training stage, collecting a large number of data representing FSOC performance from external data sources and through simulation in five feature categories; dividing the collected data into training datasets and testing datasets to train a prediction model based on a deep neural network (DNN); evaluating a prediction error by a loss function and adjusting weights and biases of hidden layers of the DNN to minimize the prediction error; repeating training the prediction model until the prediction error is smaller than or equal to a pre-set threshold; in an application stage, receiving parameters entered by a user for an application scenario; retrieving and preparing real-time data from the external data sources for the application scenario; and generating near real-time FSOC performance prediction results based on the trained prediction model.
    Type: Grant
    Filed: September 15, 2020
    Date of Patent: May 3, 2022
    Assignee: INTELLIGENT FUSION TECHNOLOGY, INC.
    Inventors: Lun Li, Yi Li, Sixiao Wei, Dan Shen, Genshe Chen
  • Patent number: 11314989
    Abstract: A system for training a generative model and a discriminative model. The generative model generates synthetic instances from latent feature vectors by generating an intermediate representation from the latent feature vector and generating the synthetic instance from the intermediate representation. The discriminative model determines multiple discriminator scores for multiple parts of an input instance, indicating whether the part is from a synthetic instance or an actual instance. The generative model is trained by backpropagation. During the backpropagation, partial derivatives of the loss with respect to entries of the intermediate representation are updated based on a discriminator score for a part of the synthetic instance, wherein the part of the synthetic instance is generated based at least in part on the entry of the intermediate representation, and wherein the partial derivative is decreased in value if the discriminator score indicates an actual instance.
    Type: Grant
    Filed: July 9, 2020
    Date of Patent: April 26, 2022
    Assignee: Robert Bosch GmbH
    Inventor: Andres Mauricio Munoz Delgado
  • Patent number: 11308363
    Abstract: A training device may include one or more processors configured to generate, using a data augmentation model, augmented sensor data for sensor data, the sensor data provided by a plurality of sensors, wherein the augmented sensor data comprise error states of one or more sensors of the plurality of sensors providing the sensor data, and to train an object detection model based on the augmented sensor data.
    Type: Grant
    Filed: March 26, 2020
    Date of Patent: April 19, 2022
    Assignee: INTEL CORPORATION
    Inventors: Julio Jarquin Arroyo, Kay-Ulrich Scholl
  • Patent number: 11308356
    Abstract: An information management apparatus comprises a communication unit configured to communicate with a plurality of external apparatuses having learning functions, and a control unit configured to control the communication with the plurality of external apparatuses performed by the communication unit. The control unit, if supervisory data generated when a predetermined external apparatus executes a learning function is received from the predetermined external apparatus via the communication unit, selects, from among the plurality of external apparatuses, an external apparatus, other than the predetermined external apparatus, with which the supervisory data is to be shared, and performs control so that the supervisory data is transmitted to the selected external apparatus.
    Type: Grant
    Filed: June 3, 2020
    Date of Patent: April 19, 2022
    Assignee: CANON KABUSHIKI KAISHA
    Inventor: Shunji Fujita
  • Patent number: 11301724
    Abstract: A system includes a camera configured to obtain image information from objects. The system also includes a processor in communication with the camera and programmed to receive an input data including the image information, encode the input via an encoder, obtain a latent variable defining an attribute of the input data, generate a sequential reconstruction of the input data utilizing at least the latent variable and an adversarial noise, obtain a residual between the input data and the sequential reconstruction utilizing a comparison of at least the input and the reconstruction to learn a mean shift in latent space, and output a mean shift indicating a test result of the input compared to the adversarial noise based on the comparison.
    Type: Grant
    Filed: April 30, 2020
    Date of Patent: April 12, 2022
    Assignee: ROBERT BOSCH GMBH
    Inventors: Liang Gou, Lincan Zou, Axel Wendt, Liu Ren
  • Patent number: 11301727
    Abstract: The present invention provides an efficient image classification method based on structured pruning, which incorporates a spatial pruning method based on variation regularization, including steps such as image data preprocessing, inputting images to neural network, image model pruning and retraining, and new image class predication and classification. The present invention adopts a structured pruning method that removes unimportant weight parameters of the original network model and reduces unnecessary computational and memory consumptions caused by the network model in image classification to simplify the image classifier, and then uses the sparsified network model to predict and classify new images. The simplified method according to the present invention improves the original network model in image classification efficiency by nearly two times, costs about 30% less memory consumption and produces a better classification result.
    Type: Grant
    Filed: July 31, 2020
    Date of Patent: April 12, 2022
    Assignee: Zhejiang University
    Inventors: Haoji Hu, Xiang Li, Huan Wang
  • Patent number: 11301723
    Abstract: A data generation device includes one or more processors. The processors input input data into a neural network and obtain an inference result of the neural network The processors calculate a first loss and a second loss. The first loss becomes smaller in value as a degree of matching between the inference result and a target label becomes larger. The target label indicates a correct answer of the inference. The second loss is a loss based on a contribution degree to the inference result of a plurality of elements included in the input data and the target label. The processors update the input data based on the first loss and the second loss.
    Type: Grant
    Filed: February 24, 2020
    Date of Patent: April 12, 2022
    Assignee: KABUSHIKI KAISHA TOSHIBA
    Inventor: Shuhei Nitta