-
公开(公告)号：US09060685B2
公开(公告)日：2015-06-23
申请号：US13850694
申请日：2013-03-26
Applicant: NEC Laboratories America, Inc.
Inventor： Eric Cosatto , Pierre-Francois Laquerre , Christopher Malon , Hans-Peter Graf
CPC classification number: A61B5/0033 , G06F19/36 , G06K9/00127 , G06K9/6227 , G06K9/6256 , G06T7/0012 , G06T2207/10056 , G06T2207/20081 , G06T2207/20084 , G06T2207/30024
Abstract: Disclosed is a computer implemented method for fully automated tissue diagnosis that trains a region of interest (ROI) classifier in a supervised manner, wherein labels are given only at a tissue level, the training using a multiple-instance learning variant of backpropagation, and trains a tissue classifier that uses the output of the ROI classifier. For a given tissue, the method finds ROIs, extracts feature vectors in each ROI, applies the ROI classifier to each feature vector thereby obtaining a set of probabilities, provides the probabilities to the tissue classifier and outputs a final diagnosis for the whole tissue.
Abstract translation: 公开了一种用于全自动组织诊断的计算机实现方法，其以受监督的方式训练感兴趣区域（ROI）分类器，其中仅在组织水平给出标签，使用反向传播的多实例学习变体的培训和火车 使用ROI分类器的输出的组织分类器。 对于给定的组织，该方法找到ROI，在每个ROI中提取特征向量，将ROI分类器应用于每个特征向量，从而获得一组概率，为组织分类器提供概率并输出整个组织的最终诊断。
-
公开(公告)号：US20130315465A1
公开(公告)日：2013-11-28
申请号：US13850694
申请日：2013-03-26
Applicant: NEC Laboratories America, Inc.
Inventor： Eric Cosatto , Pierre-Francois Laquerre , Christopher Malon , Hans-Peter Graf
CPC classification number: A61B5/0033 , G06F19/36 , G06K9/00127 , G06K9/6227 , G06K9/6256 , G06T7/0012 , G06T2207/10056 , G06T2207/20081 , G06T2207/20084 , G06T2207/30024
Abstract: Disclosed is a computer implemented method for fully automated tissue diagnosis that trains a region of interest (ROI) classifier in a supervised manner, wherein labels are given only at a tissue level, the training using a multiple-instance learning variant of backpropagation, and trains a tissue classifier that uses the output of the ROI classifier. For a given tissue, the method finds ROIs, extracts feature vectors in each ROI, applies the ROI classifier to each feature vector thereby obtaining a set of probabilities, provides the probabilities to the tissue classifier and outputs a final diagnosis for the whole tissue.
Abstract translation: 公开了一种用于全自动组织诊断的计算机实现方法，其以受监督的方式训练感兴趣区域（ROI）分类器，其中仅在组织水平给出标签，使用反向传播的多实例学习变体的培训和火车 使用ROI分类器的输出的组织分类器。 对于给定的组织，该方法找到ROI，在每个ROI中提取特征向量，将ROI分类器应用于每个特征向量，从而获得一组概率，为组织分类器提供概率并输出整个组织的最终诊断。
-
公开(公告)号：US20250148815A1
公开(公告)日：2025-05-08
申请号：US18938766
申请日：2024-11-06
Applicant: NEC Laboratories America, Inc.
Inventor： Eric Cosatto , Evgenia Tatiani Chroni
Abstract: Systems and methods for gradient-to-parameter ratio guided feature alignment for model adaptation. To adapt an artificial intelligence (AI) model to different domains, activation statistics for the AI model can be computed from collected domain data. Weights of the AI model can be adjusted based on the activation statistics of the training gradients. The AI model can be fine-tuned by focusing adaptation intensity to layers with attention mechanism by using a ratio of gradient norm over parameter norm to obtain a fine-tuned AI model. The fine-tuned AI model can be employed to perform downstream tasks such as cell segmentation from medical images.
-
34.发明申请公开(公告)号：US20240386266A1
公开(公告)日：2024-11-21
申请号：US18666088
申请日：2024-05-16
Applicant: NEC Laboratories America, Inc.
Inventor： Jonathan Warrell , Eric Cosatto , Renqiang Min , Tianci Song
IPC: G06N3/08
Abstract: A method for graph analysis includes identifying trainable control parameters of a graph refinement function. Sample graph refinements of an input graph are generated, using control parameters sampled from a variational distribution. Graph refinement control parameters associated with a sample graph refinement that has a highest performance score are selected when used to train a graph neural network. Graph analysis is performed on the input graph using the selected graph refinement parameters to produce a refined graph on new test samples. An action is performed responsive to the graph analysis.
-
公开(公告)号：US12106550B2
公开(公告)日：2024-10-01
申请号：US17711546
申请日：2022-04-01
Applicant: NEC Laboratories America, Inc.
Inventor： Eric Cosatto
IPC: G06V10/774 , G06V10/82 , G06V10/98 , G06V20/69
CPC classification number: G06V10/7753 , G06V10/82 , G06V10/98 , G06V20/69 , G06V20/698 , G06V2201/03
Abstract: Methods and systems for training a neural network model include augmenting an original training dataset to generate an augmented training dataset, by applying an image artifact to a portion of an original image of the original dataset to generate an artifact image. A target image is generated corresponding to the artifact image by deleting labels from the target image at the position of the artifact. A neural network model is trained using the augmented training dataset and the corresponding target image, the neural network model including a first output that identifies artifact regions and other outputs identifying objects.
-
Patent Agency Ranking
公开(公告)号：US12007579B2
公开(公告)日：2024-06-11
申请号：US17081900
申请日：2020-10-27
Applicant: NEC Laboratories America, Inc.
Inventor： Giovanni Milione , Philip Ji , Eric Cosatto
IPC: G02B27/28 , G06F18/214 , G06F18/24 , G06V10/764 , G06V10/82
CPC classification number: G02B27/283 , G06F18/214 , G06F18/24 , G06V10/764 , G06V10/82
Abstract: Aspects of the present disclosure describe systems, methods, and structures for the machine learning based regression of complex coefficients of a linear combination of spatial modes from a multimode optical fiber.
-
公开(公告)号：US11733089B2
公开(公告)日：2023-08-22
申请号：US17556939
申请日：2021-12-20
Applicant: NEC Laboratories America, Inc.
Inventor： Shaobo Han , Ming-Fang Huang , Eric Cosatto
IPC: G01H9/00 , H04B10/071
CPC classification number: G01H9/004 , H04B10/071
Abstract: Aspects of the present disclosure describe an unsupervised context encoder-based fiber sensing method that detects anomalous vibrations proximate to a sensor fiber that is part of a distributed fiber optic sensing system (DFOS) such that damage to the sensor fiber by activities producing and anomalous vibrations are preventable. Advantageously, our method requires only normal data streams and a machine learning based operation is utilized to analyze the sensing data and report abnormal events related to construction or other fiber-threatening activities in real-time. Our machine learning algorithm is based on waterfall image inpainting by context encoder and is self-trained in an end-to-end manner and extended every time the DFOS sensor fiber is optically connected to a new route. Accordingly, our inventive method and system it is much easier to deploy as compared to supervised methods of the prior art.
-
公开(公告)号：US11494377B2
公开(公告)日：2022-11-08
申请号：US16819947
申请日：2020-03-16
Applicant: NEC Laboratories America, Inc.
Inventor： Eric Cosatto , Alexandru Niculescu-Mizil
IPC: G06F16/2452 , G06F16/242 , G06F16/901 , G06F16/2453 , G06F16/73 , G06F40/205 , G06F40/30 , G06N7/00 , G06N20/00
Abstract: Systems and methods for solving queries on image data are provided. The system includes a processor device coupled to a memory device. The system includes a detector manager with a detector application programming interface (API) to allow external detectors to be inserted into the system by exposing capabilities of the external detectors and providing a predetermined way to execute the external detectors. An ontology manager exposes knowledge bases regarding ontologies to a reasoning engine. A query parser transforms a natural query into query directed acyclic graph (DAG). The system includes a reasoning engine that uses the query DAG, the ontology manager and the detector API to plan an execution list of detectors. The reasoning engine uses the query DAG, a scene representation DAG produced by the external detectors and the ontology manager to answer the natural query.
-
公开(公告)号：US20220319158A1
公开(公告)日：2022-10-06
申请号：US17711546
申请日：2022-04-01
Applicant: NEC Laboratories America, Inc.
Inventor： Eric Cosatto
IPC: G06V10/774 , G06V10/82 , G06V20/69 , G06V10/98
Abstract: Methods and systems for training a neural network model include augmenting an original training dataset to generate an augmented training dataset, by applying an image artifact to a portion of an original image of the original dataset to generate an artifact image. A target image is generated corresponding to the artifact image by deleting labels from the target image at the position of the artifact. A neural network model is trained using the augmented training dataset and the corresponding target image, the neural network model including a first output that identifies artifact regions and other outputs identifying objects.
-
公开(公告)号：US11120127B2
公开(公告)日：2021-09-14
申请号：US16218976
申请日：2018-12-13
Applicant: NEC Laboratories America, Inc.
Inventor： Alexandru Niculescu-Mizil , Eric Cosatto , Xavier Fontaine
Abstract: Methods and systems for detecting and correcting anomalies include predicting normal behavior of a monitored system based on training data that includes only sensor data collected during normal behavior of the monitored system. The predicted normal behavior is compared to recent sensor data to determine that the monitored system is behaving abnormally. A corrective action is performed responsive to the abnormal behavior to correct the abnormal behavior.
-
-
-
-
-
-
-
-
-
Search Results
59
records
(took 0.022 seconds)
