Mechanisms are provided to implement a generative adversarial network (GAN). A discriminator of the GAN is configured to discriminate input medical images into a plurality of classes including a first class indicating a medical image representing a normal medical condition, a second class indicating an abnormal medical condition, and a third class indicating a generated medical image. A generator of the GAN generates medical images and a training medical image set is input to the discriminator that includes labeled medical images, unlabeled medical images, and generated medical images. The discriminator is trained to classify training medical images in the training medical image set into corresponding ones of the first, second, and third classes. The trained discriminator is applied to a new medical image to classify the new medical image into a corresponding one of the first class or second class. The new medical image is either labeled or unlabeled.

Generating a risk and constraint labeled context map of an operational space is provided. The risk and constraint labeled context map of the operational space corresponding to a user of a cognitive suit is generated to drive the cognitive suit contextually using three-dimension reconstruction, virtual reality, and semi-supervised learning. Labeled risks and constraints in the risk and constraint labeled context map are associated with cognitive suit actuation events to deploy a set of mitigation strategies to address the labeled risks and constraints. An apparatus embedded in the cognitive suit is actuated to deploy the set of mitigation strategies in response to sensing a labeled risk or labeled constraint proximate to the user along a trajectory of the user in the operational space.

Aspects of the present invention disclose a method, computer program product, and system for pre-training a neural network. The method extracting features of data set received from a source, the data set includes labelled data and unlabeled data. Generating a plurality of data clusters from instances of data in the data set, the data clusters are weighted according to a respective number of similar instances of labeled data and unlabeled data within a respective data cluster. Determining a data label indicating a data class that corresponds to labeled data within a data cluster of the generated plurality of data clusters. Applying the determined data label to unlabeled data within the data cluster of the generated plurality of data clusters. In response to applying the determined data label to unlabeled data within the data cluster of the generated plurality of data clusters, deploying the data cluster to a neural network.

A deep learning training system and method, includes an imaging system for capturing medical images, a machine learning engine, and display. The machine learning engine selects a small-scale of images from a training dataset, generates global views by randomly selecting regions in one image, generates local views by randomly selecting regions covering less than a majority of the image, receives the generated global views as a first sequence of non-overlapping image patches, receives the generated global views and the generated local views as a second sequence of non-overlapping image patches, trains parameters in a student-teacher network to predict a class of objects by self-supervised view prediction using the first sequence and the second sequence. The teacher parameters are updated via exponential moving average of the student network parameters. The parameters in the teacher network are transferred to the vision transformer, and the vision transformer is trained by supervised learning.

The present application discloses a method for training a model, an electronic device and a storage medium. The method includes obtaining an image set used for training a model and discriminating the labeled image and the unlabeled image by a target sub-model of the model and determining first classification reference information of the labeled image and first classification reference information of the unlabeled image. The method further includes discriminating the unlabeled image by a non-target sub-model of the model, and determining second classification reference information of the unlabeled image and determining a classification loss of the target sub-model based on the first classification reference information of the labeled image, the category label of the labeled image, and the second classification reference information of the unlabeled image and tuning a model parameter of the model according to the classification loss.

An apparatus configured to be head-worn by a user, includes: a screen configured to present graphics for the user; a camera system configured to view an environment in which the user is located; and a processing unit coupled to the camera system, the processing unit configured to: obtain locations of features for an image of the environment, wherein the locations of the features are identified by a neural network; determine a region of interest for one of the features in the image, the region of interest having a size that is less than a size of the image; and perform a corner detection using a corner detection algorithm to identify a corner in the region of interest.

The present invention proposes a method for detecting anomalous or out-of-distribution images in a machine learning system (1) comprising a pre-training network with a first encoder, and an anomaly detection network with a second encoder. The system is first pre-trained by training the pre-training network, and then subsequently fine-tuned by training the anomaly detection network. According to one example, during pre-training, only unlabelled training images are used, while during fine-tuning, a small fraction of labelled training images is used in addition to unlabelled training images. The method can be applied to both single and multi-domain image data.

A method for training an image recognition model includes: obtaining training image sets; obtaining a first predicted probability, a second predicted probability, a third predicted probability, and a fourth predicted probability based on the training image sets by using an initial image recognition model; determining a target loss function according to the first predicted probability, the second predicted probability, the third predicted probability, and the fourth predicted probability; and training the initial image recognition model based on the target loss function, to obtain an image recognition model.

In order to provide a technique for generating a high-inference accuracy learning model in machine learning in which unlabeled data is used, an information processing apparatus includes: an acquiring section configured to acquire labeled data and unlabeled data, the labeled data being image data to which a ground-truth label and attribute information are attached, the unlabeled data being image data to which an attribute information is attached; an inter-attribute distance calculating section configured to calculate a distance between the labeled data and the unlabeled data, the distance being determined by the attribute information; an extracting section configured to extract, from multiple pieces of unlabeled data each being the unlabeled data, unlabeled data smaller in the distance from the labeled data than another unlabeled data; and an updating section configured to update a model parameter with use of the labeled data and the unlabeled data extracted by the extracting section.

A method and system of active learning that includes receiving a set of data instances, passing the set of data instances through an adaptive weighted uncertainty sampling methodology to select a set of unlabeled data instances and the determining if any of the set of unlabeled data instances need to be further processed. The AWUS methodology assigns a weighting to each of the selected unlabeled data instances whereby the weighting may be used to determine which of the set of unlabeled data instances should be further processed.