Methods, systems, and computer program products, for training a multitask neural network. First and second datasets are provided, containing samples for a first task and a second task, respectively. First and second batch miners are provided for mining samples from the first and second datasets. First and second costs for completing the first and second tasks, respectively, are assessed using a first sample mined by the first batch miner from the first dataset and a second sample mined by the second batch miner from the second dataset. When the first or second cost, respectively, falls within a range delimited by lower and upper thresholds, the is added to a first or second batch, respectively. When a termination condition is reached for either the first or second batch, the first or the second batch is used to update the neural network.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training Vision Transformer (ViT) neural networks.

A method includes obtaining first feature vectors and second feature vectors representing contents of a first and second image frame, respectively, of an input video. The method may also include generating, based on the first feature vectors, first slot vectors, where each slot vector represents attributes of a corresponding entity as represented in the first image frame, and generating, based on the first slot vectors, predicted slot vectors including a corresponding predicted slot vector that represents a transition of the attributes of the corresponding entity from the first to the second image frame. The method may additionally include generating, based on the predicted slot vectors and the second feature vectors, second slot vectors including a corresponding slot vector that represents the attributes of the corresponding entity as represented in the second image frame, and determining an output based on the predicted slot vectors or the second slot vectors.

A non-transitory computer-readable recording medium having stored therein an evaluation program for causing a computer to execute a process including: specifying a plurality of partial images included in input image data by inputting the input image data into a detection model, the detection model being a machine learning model trained with a first training data set including a plurality of first training data each associating image data with a partial image which contains an extraction target from the image data; and evaluating the input image data by inputting the plurality of specified partial images into an evaluation model, the evaluation model being a machine learning model trained with a second training data set including a plurality of second training data each associating one or more partial images with an evaluation result of a target being a subject of an image containing the one or more partial images.

Disclosed are a semi-automatic image data labeling method, an electronic apparatus and a non-transitory computer-readable storage medium. The semi-automatic image data labeling method may include: displaying a to-be-labeled image, the to-be-labeled image comprising a selected area and an unselected area; acquiring a coordinate point of the unselected area and a first range value; executing a grabcut algorithm based on the coordinate point of the unselected area and the first range value acquired, and obtaining a binarized image divided by the grabcut algorithm; executing an edge tracking algorithm on the binarized image to acquire current edge coordinates; updating a local coordinate set based on the current edge coordinates acquired; updating the selected area of the to-be-labeled image based on the local coordinate set acquired.

A learning device includes a class classification learning unit that learns class classification of a classification target by using a loss function in which a loss is calculated to become smaller as a magnitude of a difference between a function value obtained by inputting a log-likelihood ratio to a function having a finite value range and a constant associated with a correct answer to the class classification of the classification target becomes smaller, the log-likelihood ratio being the logarithm of a ratio between the likelihood that the classification target belongs to a first class and the likelihood that the classification target belongs to a second class.

A part inspection system includes a vision device configured to image a part being inspected and generate a digital image of the part. The inspection system includes a part inspection module communicatively coupled to the vision device and receiving the digital image of the part. The part inspection module includes an image quality module. The image quality module analyzes the digital image to determine if the digital image achieves a quality threshold. The image quality module generates an image quality output based on the analysis of the digital image. The part inspection module includes an image classifier module. The image classifier module analyzes the digital image to classify the image as a defective part or a non-defective part.

Computer-implemented methods and systems are provided for digitally signing predetermined arrays of digital data. Such a method may provide a secret neural network model trained to classify arrays of digital data in dependence on data content of the arrays. The array of the arrays may be signed by supplying the array to the secret neural network model to obtain an initial classification result; and effecting a modification of data in the array to change the initial classification result to a predetermined, secret classification result, the modification being effected via a backpropagation process in the secret neural network model to progressively modify the array in response to backpropagated errors dependent on a difference between a current classification result for the array and the secret classification result.

A method for selecting a deep learning network which is optimal for solving an image processing task obtaining a type of the image processing task, selecting a data set according to the type of problem, and dividing selected data set into training data and test data. Similarities between different training data are calculated, and a batch size of the training data is adjusted according to the similarities of the training data. A plurality of deep learning networks is selected according to the type of problem, and the plurality of deep learning networks is trained through the training data to obtain network models. Each of the network models is tested through the test data, and the optimal deep learning network with the best test result is selected from the plurality of deep learning networks appropriate for image processing.

Provided is an information processing apparatus that performs human emotion recognition using artificial intelligence.

The information processing apparatus includes: a preprocessing unit that determines whether or not to permit provision of a service based on emotion recognition on the basis of a predetermined criterion; an emotion estimation processing unit that performs the emotion recognition for a user by using an artificial intelligence function; and a service providing processing unit that provides a service based on an emotion recognition result by the emotion estimation processing unit, in which, when the preprocessing unit determines to permit the provision of the service, the emotion estimation processing unit performs the emotion recognition or the service providing processing unit provides the service.