公开(公告)号：US20240005655A1

公开(公告)日：2024-01-04

申请号：US18247493

申请日：2020-10-21

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Mihiro UCHIDA ,  Jun SHIMAMURA ,  Shingo ANDO ,  Takayuki UMEDA

IPC: G06V10/98 ,  G06V10/774 ,  G06V10/764 ,  G06V10/82

CPC classification number: G06V10/98 ,  G06V10/774 ,  G06V10/764 ,  G06V10/82

Abstract: A learning apparatus includes: a data generation unit that learns generation of data based on a class label signal and a noise signal; an unknown degree estimation unit that learns estimation of a degree to which input data is unknown using a training set and the data generated by the data generation unit; a first class likelihood estimation unit that learns estimation of a first likelihood of each class label for input data using the training set; a second class likelihood estimation unit that learns estimation of a second likelihood of each class label for input data using the training set and the data generated by the data generation unit; a class likelihood correction unit that generates a third likelihood by correcting the first likelihood on the basis of the unknown degree and the second likelihood; and a class label estimation unit that estimates a class label of data related to the third likelihood on the basis of the third likelihood, thereby automatically estimating a cause of an error by a deep model.

公开(公告)号：US20220019899A1

公开(公告)日：2022-01-20

申请号：US17312364

申请日：2019-12-02

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Kazuhiko MURASAKI ,  Chihiro SAITO ,  Shingo ANDO ,  Atsushi SAGATA

IPC: G06N3/08

Abstract: A weft-balanced detector can be trained in the vicinity of a desired TPR or PPR. A range determined by an upper limit and a lower limit of a. true positive rate or a false positive rate for defining a part of an area under a ROC curve is set so as to be narrowed at each repetition, a score function is trained so as to optimize an objective function represented using positive example data selected from ranked positive example data, negative example data, and the score function that calculates a score representing likelihood of a positive example according to the set range between the upper limit and the lower limit of the true positive rate or the false positive rate, the positive example data is ranked, the maximization learning unit and the ranking unit repeats the processing until the objective function is converged, and the region-to-be-maximized setting unit repeats setting until the range between the upper limit and the lower limit of the true positive rate or the false positive rate becomes a predetermined size.

公开(公告)号：US20210357698A1

公开(公告)日：2021-11-18

申请号：US17277248

申请日：2019-09-06

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Kazuhiko MURASAKI ,  Shingo ANDO ,  Atsushi SAGATA

IPC: G06K9/62

Abstract: An object is to make it possible to train an image recognizer by efficiently using training data that does not include label information. A determination unit 180 causes repeated execution of the followings. A feature representation model for extracting feature vectors of pixels is trained such that an objective function is minimized, the objective function being expressed as a function that includes a value that is based on a difference between a distance between feature vectors of pixels labeled with a positive example label and a distance between a feature vector of a pixel labeled with the positive example label and a feature vector of an unlabeled pixel, and a value that is based on a difference between a distance between a feature vector of a pixel labeled with the positive example label and a feature vector of an unlabeled pixel and a distance between a feature vector of a pixel labeled with the positive example label and a feature vector of a pixel labeled with a negative example label, and based on a distribution of feature vectors corresponding to the positive example label, a predetermined number of labels are given based on the likelihood that each unlabeled pixel is a positive example.

公开(公告)号：US20240281711A1

公开(公告)日：2024-08-22

申请号：US18548148

申请日：2021-03-23

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Mihiro UCHIDA ,  Takayuki UMEDA ,  Shingo ANDO ,  Jun SHIMAMURA

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: There is provided a class label estimation device that estimates a class label of input data and estimates a cause of an estimation error, the class label estimation device including: a distribution estimation unit that estimates a distribution followed by a training set; a distance estimation unit that estimates a distance of the input data from the training set based on the distribution; an unknown degree estimation unit that estimates an unknown degree of the input data based on the distance; an unknown degree correction unit that corrects the unknown degree based on the distribution; and an error cause estimation unit that estimates a cause of an estimation error using the corrected unknown degree.

公开(公告)号：US20230040195A1

公开(公告)日：2023-02-09

申请号：US17792655

申请日：2020-01-15

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Kana KURATA ,  Yasuhiro YAO ,  Shingo ANDO ,  Jun SHIMAMURA

IPC: G01S13/89 ,  G06K9/00 ,  G06N5/04

Abstract: A class label of a three-dimensional point cloud can be identified with high performance. The key point choice unit 22 extracts a key point cloud 35 including three-dimensional points efficiently representing features of an object and a non-key point cloud 37. A inference unit 24 takes, as representative points, a plurality of points selected by down-sampling from each of the key point cloud 35 and the non-key point cloud 37, extracts, with respect to each of the representative points, a feature of each representative point from coordinates and the feature of the representative point and coordinates and features of neighboring points positioned near the representative point. The inference unit 24 extracts features of a plurality of new representative points from the coordinates and the features of the plurality of representative points, coordinates and features of a plurality of three-dimensional points before sampling which are the new representative points, and coordinates and features of neighboring points positioned near the new representative points. The inference unit 24 derives a class label from the coordinates and features of the plurality of representative points, or the coordinates and features of the plurality of new representative points, and outputs the class label.

公开(公告)号：US20220392193A1

公开(公告)日：2022-12-08

申请号：US17775837

申请日：2019-11-11

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Yasuhiro YAO ,  Hitoshi NIIGAKI ,  Shingo ANDO ,  Jun SHIMAMURA

IPC: G06V10/762 ,  G06V10/77 ,  G06V10/82

Abstract: A clustering unit (101) divides an input three-dimensional point cloud into a plurality of clusters and outputs cluster data, a surrounding point sampling unit (102) extracts, for each of the plurality of clusters, a surrounding three-dimensional point cloud present within a predetermined distance of the cluster based on the three-dimensional point cloud and the cluster data, a learning unit (103) receives, as inputs, extended cluster data including information on a three-dimensional point cloud included in each cluster obtained by the division and information on the extracted surrounding three-dimensional point cloud and a correct answer label indicative of an object to which the three-dimensional point cloud included in each cluster belongs, and learns a parameter of a DNN for estimating a label of each cluster from the extended cluster data, and an estimation unit (104) inputs the extended cluster data related to the cluster of which the label is unknown to the DNN of which the parameter is trained to estimate the label of each cluster.

公开(公告)号：US20200378898A1

公开(公告)日：2020-12-03

申请号：US16970876

申请日：2019-02-06

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Shunsuke TSUKATANI ,  Shingo ANDO ,  Tetsuya KINEBUCHI

IPC: G01N21/88 ,  G01N21/55 ,  G01N21/31 ,  G06N20/00 ,  G06N5/04

Abstract: Even under a different light source, such as outdoor light source, diagnosis of surface states of a diagnosis target object is performed with a high accuracy without measuring spectral distribution information about the light source at the time of measuring a diagnosis target object. A spectral reflectance calculation section (22) calculates, based on pieces of spectral distribution information measured for different surface states of a diagnosis target object and spectral distribution information measured for a reference object with an already-known reflectance, spectral reflectances of the surface states; a reference setting section (23) sets, from a spectral reflectance of a surface state showing a deteriorated state, among the spectral reflectances of the surface states, a wavelength range within which reflectances at the same wavelength are within a predetermined range and the reflectance as a reference wavelength range and a reference reflectance; and a dictionary registration section (24) registers the spectral reflectances of the surface states, the reference wavelength range, the reference reflectance and pieces of spectral distribution information about a plurality of light sources with a dictionary (30).

公开(公告)号：US20230409964A1

公开(公告)日：2023-12-21

申请号：US18035090

申请日：2020-11-05

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Kana KURATA ,  Yasuhiro YAO ,  Naoki ITO ,  Shingo ANDO ,  Jun SHIMAMURA

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: An identification device acquires a plurality of identification target points by sampling a target point group that is a set of three-dimensional target points. The identification device calculates relative coordinates of a neighboring point of the identification target point with respect to the identification target point. The identification device inputs coordinates of the plurality of identification target points and relative coordinates of neighboring points with respect to each of the plurality of identification target points into a class label assigning learned model to acquire class labels of the plurality of identification target points and validity of the class labels with respect to the neighboring points for each of the plurality of identification target points. The identification device assigns the class labels to the plurality of identification target points, assigns the class labels to the neighboring points for each of the plurality of identification target points when the validity of the class label is included in a range determined by a predetermined threshold value, and identifies the class labels of the identification target point and the neighboring point.

公开(公告)号：US20220335085A1

公开(公告)日：2022-10-20

申请号：US17631396

申请日：2019-07-30

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Shunsuke TSUKATANI ,  Kazuhiko MURASAKI ,  Shingo ANDO ,  Atsushi SAGATA

IPC: G06F16/906

Abstract: A data selection method selects, based on a set of labeled first data pieces and a set of unlabeled second data pieces, a target to be labeled from the set of the second data pieces. The method includes: a classification procedure classifying data pieces belonging to the set of the first data pieces and data pieces belonging to the set of the second data pieces into clusters of the number at least one more than the number of types of the labels; and a selection procedure selecting the second data piece to be labeled from a cluster, from among the clusters, that does not include the first data piece, each of the procedures being performed by a computer. Thereby, it is possible to select the data piece to be labeled, which is effective for a target task, from among data sets of unlabeled data pieces.

公开(公告)号：US20220230347A1

公开(公告)日：2022-07-21

申请号：US17608975

申请日：2019-05-08

Applicant: NIPPON TELEGRAPH AND TELEPHONE CORPORATION

Inventor： Hitoshi NIIGAKI ,  Masaki WAKI ,  Masaaki INOUE ,  Yasuhiro YAO ,  Tomoya SHIMIZU ,  Hiroyuki OSHIDA ,  Kana KURATA ,  Shingo ANDO ,  Atsushi SAGATA

IPC: G06T7/66 ,  G06V10/25 ,  G06V10/75

Abstract: It is possible to estimate a slack level accurately in consideration of a shape of a deformed cable. A point cloud analysis device sets a plurality of regions of interest obtained by window-searching a wire model including a quadratic curve model representing a cable obtained from a point cloud consisting of three-dimensional points on an object, the region of interest being divided into a first region and a second region. The point cloud analysis device compares information on the first region with information on the second region based on the point cloud included in the region of interest and the quadratic curve model for each of the plurality of regions of interest, calculates a degree of division boundary representing a degree to which a division position between the first region and the second region of the plurality of regions of interest is a branch point of the cable, and detects a division boundary point that is a branch point of a cable represented by the quadratic curve model based on the degree of division boundary calculated for each of the plurality of regions of interest.