A calculation unit calculates a first error for a boundary region of an image represented by image data, calculates a second error for a non-boundary region different from the boundary region, and calculates an error between label data and an estimation result based on the first error and the second error. And an influence of the first error on the calculation by the calculation unit is controlled to be smaller than an influence of the second error on the calculation by the calculation unit.

A calculation unit calculates a first error for a boundary region of an image represented by image data, calculates a second error for a non-boundary region different from the boundary region, and calculates an error between label data and an estimation result based on the first error and the second error. And an influence of the first error on the calculation by the calculation unit is controlled to be smaller than an influence of the second error on the calculation by the calculation unit.

Systems, methods, and other embodiments for selecting, enriching and sequencing digital media content to produce a narrative-oriented, ordered sub-collection of media such as for movie creation. The method identifies, evaluates, assesses, stores, enriches, groups, and sequences content. The method identifies the content metadata. When metadata are missing or anomalous, the method attempts to populate or correct the metadata and store that new content in the database. The method evaluates content for focus quality and may exclude content based on rules. The method assesses the content storing the people and their emotional level, animals, objects, locations, landmarks and date/time in the database. The method can then enrich the remaining content by providing map, photo, video, text, and audio content. The method uses selecting criteria for grouping and sequencing content by date, time, person, etc. and compiling the sequenced groups into the final narrative ready for distribution, e.g., movie creation.

A neural network model training method and an apparatus for complex characteristic classification and common localization are proposed. In the method, a neural network model includes: a convolution layer for performing a convolution operation on an input image by using a convolution filter; a pooling layer for performing pooling on an output of the convolution layer; and class-specific fully connected layers respectively corresponding to classes into which complex characteristics are classified and outputting values obtained by multiplying an output of the pooling layer by class-specific weights (w.sub.fc(T.sub.t)). The method includes: (a) inputting the input image to the convolution layer; (b) calculating class-specific observation maps for respective classes on the basis of the output of the convolution layer; (c) calculating an observation loss (L.sub.obs) common to the classes on the basis of the class-specific observation maps; and (d) back-propagating a loss based on the observation loss to the neural network model.

This machine-learning device is provided with: a detection unit which detects a loss of consistency with a lapse of time in a determination result for unit data, the determination result being output from a determination unit that generates a learning model to be used when performing prescribed determination for one or more pieces of the unit data that form time series data; and a selection unit which selects, on the basis of the result of detection by the detection unit, unit data to be used as teacher data when the determination unit updates the learning model, thereby efficiently raising the accuracy of the learning model when machine learning is performed on the basis of the time series data.

An analysis apparatus according to one or more embodiments may identify the classes of features included in object data using a plurality of discriminators that are respectively configured to discriminate the presence of features of classes different to each other; and determines that a first data portion, with respect to which discrimination is established by one of the plurality of discriminators, but discrimination is not established by the remaining discriminators, includes a feature of the particular class that is discriminated by the one discriminator, and determines that a second data portion, with respect to which discrimination is established by all of the discriminators including the one discriminator, does not include a feature of that particular class.

A novel system and method for accurate detection and quantification of fibrous tissue produces a virtual medical image of tissue treated with a second stain based on a received medical image of tissue treated with a first stain using a computer-implemented trained deep learning model. The model is trained to learn the deep texture patterns associated with collagen fibers using conditional generative adversarial networks to detect and quantify fibrous tissue.

Described herein are means for implementing annotation-efficient deep learning models utilizing sparsely-annotated or annotation-free training, in which trained models are then utilized for the processing of medical imaging. An exemplary system includes at least a processor and a memory to execute instructions for learning anatomical embeddings by forcing embeddings learned from multiple modalities; initiating a training sequence of an AI model by learning dense anatomical embeddings from unlabeled date, then deriving application-specific models to diagnose diseases with a small number of examples; executing collaborative learning to generate pretrained multimodal models; training the AI model using zero-shot or few-shot learning; embedding physiological and anatomical knowledge; embedding known physical principles refining the AI model; and outputting a trained AI model for use in diagnosing diseases and abnormal conditions in medical imaging. Other related embodiments are disclosed.

A target detection system suitable for an embedded device, comprising an embedded device (5) and a server (6); target detection logic (5.1) running in the embedded device (5) is composed of a multi-layer shared base network, a private base network, and a detection module; a parameter of the shared base network directly comes from an output of an upper layer; and an image is processed by the shared base network and the private base network to obtain a feature map, and after being processed by the detection module, a result merging module merges and outputs a target detection result. The target detection system further comprises an online model self-calibration system. After collecting a sample, the embedded device (5) irregularly uploads the sample to the server (6), and after labeling the sample by means of automatic and manual methods, the server (6) trains a model and updates same to the embedded device (5). The target detection system can perform well in an embedded device (5), uses a large-scale target detection model on a server (6) to complete automatic labeling which reduces workload, and completes model correction more efficiently.

A target detection system suitable for an embedded device, comprising an embedded device (5) and a server (6); target detection logic (5.1) running in the embedded device (5) is composed of a multi-layer shared base network, a private base network, and a detection module; a parameter of the shared base network directly comes from an output of an upper layer; and an image is processed by the shared base network and the private base network to obtain a feature map, and after being processed by the detection module, a result merging module merges and outputs a target detection result. The target detection system further comprises an online model self-calibration system. After collecting a sample, the embedded device (5) irregularly uploads the sample to the server (6), and after labeling the sample by means of automatic and manual methods, the server (6) trains a model and updates same to the embedded device (5). The target detection system can perform well in an embedded device (5), uses a large-scale target detection model on a server (6) to complete automatic labeling which reduces workload, and completes model correction more efficiently.