Abstract: An information processing method performed by a computer includes: obtaining prediction results that are results of prediction performed by predictors on same input data; obtaining, for each of the prediction results, an influence that the input data had on the prediction result; determining, based on the prediction results, one or more combinations of the prediction results; and presenting, side by side or by superposition, using a presentation device, influences obtained for prediction results that are included in the prediction results and are in a same combination among the one or more combinations.

Abstract: An information processing apparatus includes: an obtainer that obtains sensing data; a common neutral network (NN) that inputs the sensing data into an inference model to obtain a result of inference and information on a processing time for a plurality of tasks subsequent to the processing performed by the inference model; and an NN inference computation management unit that determines a task schedule for a task processing unit that processes the plurality of subsequent tasks to process the plurality of subsequent tasks on the basis of the information on the processing time for the plurality of subsequent tasks and inputs the result of the inference into the task processing unit to process the plurality of subsequent tasks according to the determined task schedule.

Abstract: A control device includes a parameter acquisition unit that acquires an augmentation parameter regarding geometric augmentation or optical augmentation of training data to be used for training a machine learning model, a display controller that causes a display device to display an image based on the augmentation parameter, an imaging controller that causes an imaging device to capture the displayed image, and an output unit that outputs the captured image obtained by the imaging device as the training data.

Abstract: Provided is a learning device that acquires computational imaging information of a computational imaging camera that captures an image with blurring; acquires a normal image captured by a normal camera that captures an image without blurring or an image with blurring smaller than that of the computational imaging camera, and a correct answer label assigned to the normal image; generates an image with blurring based on the computational imaging information and the normal image; and performs machine learning using the image with blurring and the correct answer label to create an image identification model for identifying an image captured by the computational imaging camera.

Abstract: An image processing device includes a noise adder that obtains a captured image from an image capturing device including a mask having at least one aperture, an MPH information obtainer that obtains aperture pattern information corresponding to the pattern of the at least one aperture, the noise adder that adds, to the captured image, noise determined according to the aperture pattern information, and a transmitter that outputs the noise added captured image.

Abstract: An interval between a pinhole and a pinhole is set to a first interval at which a degree of superimposition of subject images captured through the corresponding pinholes falls within a predetermined range when an image of a subject located at a distance less than a predetermined distance from the multi-pinhole camera is captured. An interval between the pinhole and a pinhole is set to a second interval narrower than the first interval at which a degree of superimposition of subject images captured through the corresponding pinholes falls within a predetermined range when an image of the subject located at a distance equal to or more than the predetermined distance from the multi-pinhole camera is captured.

Abstract: A work estimation method includes: obtaining first sound information related to a reflected sound that is a sound obtained by reflection of an emission sound in an inaudible frequency range and second sound information related to a work sound generated by a work performed by the person; outputting image information that indicates a work area of the person by inputting the first sound information to a first trained model; outputting tool information that indicates a tool that is being used by the person, by inputting the second sound information to a second trained model; and outputting work information that indicates the content of the work, by inputting the image information and the tool information to a third trained model.

Abstract: A training data generation method for generating training data for training a recognition model that is input with image data and outputs one of a plurality of classes as a class of an object present in the image data, the training data generation method including: selecting a first class from the plurality of classes based on a recognition accuracy of the recognition model; calculating an inter-class distance that is a distance between the first class and each of two or more other classes among the plurality of classes; selecting a second class for generating the training data from the two or more other classes, based on the inter-class distance; and generating the training data by mixing image data and labels of each of the first class selected and the second class selected.

Abstract: An estimation method includes obtaining first sound information regarding a reflected sound resulted from reflection of a transmission sound in an inaudible band inside a facility, and outputting image information indicating a living body presence area in which a living body is present, by inputting the first sound information obtained to a first trained model trained using sound information regarding the reflected sound and an image indicating the living body presence area.

Abstract: An imaging control device includes a correct answer information acquiring part that acquires first correct answer information corresponding to a training image of a machine learning model from a first storage part, a correct answer image display control part that causes a display device to display a first correct answer image based on the first correct answer information, an imaging control part that causes an imaging device that acquires a blurred image to capture the first correct answer image displayed on the display device and acquires a second correct answer image, a correct answer information generating part that generates second correct answer information based on the second correct answer image, and a storage control part that stores a data set including a set of the training image and the second correct answer information in a second storage part.

Abstract: A training method includes: obtaining an image and a distance image corresponding to the image; cutting a partial area out from the distance image obtained; generating an embedded image by pasting the partial area cut out from the distance image onto a predetermined area in the image, where the predetermined area is located at a position corresponding to the position of the partial area and has a size corresponding to the size of the partial area; and training a machine learning model, using training data including the embedded image as input data and the distance image as correct answer data.

Abstract: An imaging control device includes an image acquiring part that acquires a first training image of a machine learning model, a display control part that causes a display device to display the first training image based on a distance between the display device and an imaging device that acquires a blurred image, an imaging control part that causes the imaging device to capture the first training image to acquire a second training image, and a storage control part that stores a data set including a set of the second training image and correct answer information. The display control part changes, when the distance is changed, a display size of the first training image so that a size of the second training image acquired by the imaging device is maintained. The imaging control part causes the imaging device to capture the first training image when the distance is changed.

Abstract: An information processing method includes: obtaining sensing data; determining a synthesis region in the sensing data in which recognition target data is to be synthesized with the sensing data; generating composite data by synthesizing the recognition target data into the synthesis region, the recognition target data having same or similar characteristics perceived by a human sensory system as the sensing data; obtaining recognition result data by providing the composite data to a model which has been trained using machine learning to recognize a recognition target; making a second determination based on the recognition result data and reference data including at least the synthesis region, the second determination being to determine whether to make a first determination, the first determination being to determine training data for the model based on the composite data; and making the first determination when it is determined in the second determination to make the first determination.

Abstract: An information processing method includes obtaining a first inference result by a first inference model, obtaining a second inference result by a second inference model, and training the second inference model by machine learning to reduce an error calculated from the first inference result and the second inference result. The second inference model includes (a) a first coefficient pertaining to a domain and used for inference by the second inference model and (b) a second coefficient used for inference by the second inference model. The training includes; when it is determined that a predetermined condition is not satisfied, training the second inference model with the first coefficient and the second coefficient designated as targets for an update; and when it is determined that the predetermined condition is satisfied, training the second inference model with the second coefficient designated as a target for an update.

Abstract: A control device includes: an image acquisition unit that acquires an image obtained by imaging by an imaging device in which a mask having a plurality of pinholes is arranged so as to cover a light receiving surface of an imaging element; a control unit that controls at least one of a size and an interval of two pinholes among the plurality of pinholes based on the image; and an output unit that outputs an image obtained by the imaging device after at least one of the size and the interval of the two pinholes is controlled.

Abstract: Provided is an information processing method that includes: performing a conversion process on the first feature information to obtain a first conversion result; performing the conversion process on the second feature information to obtain a second conversion result; performing a projection process on the first conversion result to obtain a first projection result; performing the projection process on the second conversion result to obtain a second projection result; calculating an error between the first projection result and the second projection result; and training the second model to reduce the error. The conversion process produces an error between the first projection result and the second projection result that is greater than the error between a projection result obtained by performing the projection process on the first feature information and a projection result obtained by performing the projection process on the second feature information.

Abstract: An information processing method includes processing of: acquiring, from a plurality of time-series images in which an object is captured, first information including at least a plurality of positions or a plurality of sizes of the object; executing prediction processing of predicting second information including at least one of a position or a size of the object at a next time point in a time-series based on the first information and recursively executing the prediction processing based on the first information and the second information to predict the second information of the object at a time point further next to the next time point; executing recognition processing of recognizing motion of the object based on the second information; and determining a total number of times of recursion of the prediction processing based on a result of the recognition processing.

Abstract: A risk prediction method is executed by a computer of a risk predictor using a convolutional neural network. The method includes making the convolutional neural network acquire an input image taken by an in-vehicle camera installed on a vehicle. The method also includes making the convolutional neural network estimate a risk area and a feature of the risk area, the risk area being in the acquired input image. The risk area has a possibility that a moving object may appear from the risk area into a travelling path of the vehicle, and the moving object may collide with the vehicle in a case where the vehicle simply continues running. The method further includes making the convolutional neural network output the estimated risk area and the estimated feature of the risk area as a risk predicted for the input image.

Abstract: An information processing method includes acquiring first output data for input data of first learning model, reference data for the input data, and second output data for the input data of second learning model obtained by converting first learning model; calculating first difference data corresponding to a difference between the first difference data and the reference data and second difference data corresponding to a difference between the second output data and the reference data; and training first learning model with use of the first difference data and the second difference data.

Abstract: In a data processing method executed by a computer: inputting, in a third trained model, first output data corresponding to first input data for a first trained model to obtain second output data, the third trained model being acquired through training in which (i) output data of the first trained model is used as training data, and (ii) output data of a second trained model acquired by converting the first trained model is used as label data; obtaining first label data of the first input data; and retraining the first trained model using first differential data corresponding to differences between the second output data and the first label data.