Abstract: A point group including a small number of points that have been assigned labels is taken as an input to assign labels to points that have not been assigned labels.

Abstract: A three-dimensional point cloud label learning and estimation device includes: a clustering unit that clusters a three-dimensional point cloud into clusters; a learning unit that makes a neural network learn to estimate a label corresponding to an object to which points contained in each of the clusters belong; and an estimation unit that estimates a label for the cluster using the neural network learned at the learning unit. In the three-dimensional point cloud label learning and estimation device, the neural network uses a total sum of sigmoid function values (sum of sigmoid) when performing feature extraction on the cluster.

Abstract: Labels can be accurately identified even for an image with a resolution not used in training data. Based on an input image, a resolution of the input image, and a resolution of a training image used for training a trained model of assigning labels to pixels of an image, a plurality of low-resolution images are generated from the input image by using a plurality of shift amounts for a pixel correspondence between the input image and the respective low-resolution images with a resolution corresponding to the training image, the low-resolution images are input to the trained model, a plurality of low-resolution label images is output in which pixels of the respective low-resolution images are assigned labels, and a label image is output in which labels for pixels of the input image are obtained, based on the shift amounts used for generating the low-resolution images and the low-resolution label images.

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.

Abstract: Simultaneous learning of a plurality of different tasks and domains, with low costs and high precision, is enabled. A learning unit 160, on the basis of learning data, uses a target encoder that takes data of a target domain as input and outputs a target feature expression, a source encoder that takes data of a source domain as input and outputs a source feature expression, a common encoder that takes data of the target domain or the source domain as input and outputs a common feature expression, a target decoder that takes output of the target encoder and the common encoder as input and outputs a result of executing a task with regard to data of the target domain, and a source decoder that takes output of the source encoder and the common encoder as input and outputs a result of executing a task with regard to data of the source domain, to learn so that the output of the target decoder matches training data, and the output of the source decoder matches training data.

Abstract: A training unit 24 performs leaning of a recognizer that recognizes labels of data based on a plurality of training data to which training labels are given. A score calculation unit 28 calculates a score output by the recognizer for each of the plurality of training data by using the trained recognizer. A threshold value determination unit 30 determines a threshold value for the score for determining the label, based on a shape of an ROC curve representing a correspondence between a true positive rate and a false positive rate, which is obtained based on the score calculated for each of the plurality of training data. A selection unit 32 selects the training data difficult to recognize by the recognizer based on the threshold value determined and the score calculated for each of the plurality of training data. The process of each unit described above is repeated until a predetermined iteration termination condition is satisfied.

Abstract: A candidate detection unit 118 detects, for each of a plurality of target images, candidate regions representing a specific detection target region using a discriminator. A region-label acquisition unit 120 acquires, for a part of the target images, position information of a search region as a teacher label. A region specifying unit 121 imparts, based on the part of the target images and the acquired position information of the search region, the position information of the search region to each of the target images, which are not the part of the target images, in semi-supervised learning processing. A filtering unit 122 outputs, for each of the acquired plurality of target images, among the candidate regions, a candidate region, an overlapping degree of which with the search region is equal to or larger than a fixed threshold.

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.

Abstract: A point group including a small number of points that have been assigned labels is taken as an input to assign labels to points that have not been assigned labels.

Abstract: A three-dimensional point cloud label learning and estimation device includes: a clustering unit that clusters a three-dimensional point cloud into clusters; a learning unit that makes a neural network learn to estimate a label corresponding to an object to which points contained in each of the clusters belong; and an estimation unit that estimates a label for the cluster using the neural network learned at the learning unit. In the three-dimensional point cloud label learning and estimation device, the neural network uses a total sum of sigmoid function values (sum of sigmoid) when performing feature extraction on the cluster.

Abstract: Labels can be accurately identified even for an image with a resolution not used in training data. Based on an input image, a resolution of the input image, and a resolution of a training image used for training a trained model of assigning labels to pixels of an image, a plurality of low-resolution images are generated from the input image by using a plurality of shift amounts for a pixel correspondence between the input image and the respective low-resolution images with a resolution corresponding to the training image, the low-resolution images are input to the trained model, a plurality of low-resolution label images is output in which pixels of the respective low-resolution images are assigned labels, and a label image is output in which labels for pixels of the input image are obtained, based on the shift amounts used for generating the low-resolution images and the low-resolution label images.

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.

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.

Abstract: Simultaneous learning of a plurality of different tasks and domains, with low costs and high precision, is enabled. A learning unit 160, on the basis of learning data, uses a target encoder that takes data of a target domain as input and outputs a target feature expression, a source encoder that takes data of a source domain as input and outputs a source feature expression, a common encoder that takes data of the target domain or the source domain as input and outputs a common feature expression, a target decoder that takes output of the target encoder and the common encoder as input and outputs a result of executing a task with regard to data of the target domain, and a source decoder that takes output of the source encoder and the common encoder as input and outputs a result of executing a task with regard to data of the source domain, to learn so that the output of the target decoder matches training data, and the output of the source decoder matches training data.