The present disclosure relates to a training method and a training system for training a learning network for medical image analysis. The training method includes: acquiring an original training data set for a learning network with a predetermined structure; performing, by a processor, a pre-training on the learning network using the original training data set to obtain a pre-trained learning network; evaluating, by the processor, the pre-trained learning network to determine whether the pre-trained learning network has an evaluation defect; when the pre-trained learning network has the evaluation defect, performing, by the processor, a data augmentation on the original training data set for the existing evaluation defect; and performing, by the processor, a refined training on the pre-trained learning network using a data augmented training data set. The present disclosure can evaluate and train the learning network in stages, therefore, the complexity of medical image processing is reduced, and the efficiency and accuracy of medical image analysis are improved.

A data generation apparatus (2) has: an obtaining unit (21) that obtains real data (D_real); a fake data generating unit (22) that generates fake data (D_fake) that imitates the real data; and a mix data generating unit (23) that generates mix data (D_mix) by mixing the real data and the fake data at a desired mix ratio (a), the mix data generating unit changes the mix ratio that is used to generate a data element of the mix data based on a position of the data element in the mix data.

Provided in embodiments of the present application are a method and device for age estimation. The method comprises: performing gender training with respect to a gender model on the basis of facial image samples so as to allow the gender model to converge, where the gender model comprises at least two convolution layers; performing age training with respect to an age model on the basis of the facial samples so as to allow the age model to converge, where the age model comprises the at least two convolution layers, the converged age model comprises the weights of the at least two convolution layers, and the weights of the at least two convolution layers that the converged gender model comprises; and performing age estimation with respect to an inputted facial image on the basis of the converged age model. The technical solution provided in the embodiments of the present application eliminates the problem of inaccurate age estimation as a result of gender differences of facial images, thus increasing the accuracy of age estimation.

An object recognition device 80 includes a scene determination unit 81, a learning-model selection unit 82, and an object recognition unit 83. The scene determination unit 81 determines, based on information obtained during driving of a vehicle, a scene of the vehicle. The learning-model selection unit 82 selects, in accordance with the determined scene, a learning model to be used for object recognition from two or more learning models. The object recognition unit 83 recognizes, using the selected learning model, an object in an image to be photographed during driving of the vehicle.

A computer-implemented method of learning sensory media association includes receiving a first type of nontext input and a second type of nontext input; encoding and decoding the first type of nontext input using a first autoencoder having a first convolutional neural network, and the second type of nontext input using a second autoencoder having a second convolutional neural network; bridging first autoencoder representations and second autoencoder representations by a deep neural network that learns mappings between the first autoencoder representations associated with a first modality and the second autoencoder representations associated with a second modality; and based on the encoding, decoding, and the bridging, generating a first type of nontext output and a second type of nontext output based on the first type of nontext input or the second type of nontext input in either the first modality or the second modality.

Disclosed herein is digital object generator that makes uses a one-way function to generate unique digital objects based on the user specific input. Features of the input are first extracted via a few-shot convolutional neural network model, then evaluated weight and integrated fit. The resulting digital object includes a user decipherable output such as a visual representation, an audio representation, or a multimedia representation that includes recognizable elements from the user specific input.

A method for extracting an oil storage tank based on a high-spatial-resolution remote sensing image is provided, including: acquiring an oil storage tank sample, and randomly dividing the oil storage tank sample into a training set and a testing set; building an oil storage tank extraction model based on a Res2-Unet model structure, wherein the Res2-Unet is a deep learning network based on a UNet semantic segmentation structure, and a Res2Net convolution block is configured to change a feature interlayer learning to a granular learning and is arranged in a residual mode; and performing a precision verification on the testing set.

This disclosure describes systems, methods, and devices related to automatic annotation. A device may capture data associated with an image comprising an object. The device may acquire input data associated with the object. The device may estimate a plurality of points within a frame of the image, wherein the plurality of point constitute a 3D bounding to around the object. The device may transform the plurality of points to two or more 2D points. The device may construct a bounding box that encapsulates the object using the two or more 2D points. The device may create a segmentation mask of the object using morphological techniques. The device may perform annotation based on the segmentation mask.

There are provided machine learning device and method which can prepare divided data suitable for machine learning from volume data for learning. A machine learning unit (15) calculates detection accuracy of each organ O(j,i) in a predicted mask Pj using a loss function Loss. However, the detection accuracy of the organ O(k,i) with a volume ratio A(k,i)<Th is not calculated. That is, in the predicted mask Pk, the detection accuracy of the organ O(k,i) with a volume ratio that is small to some extent is ignored. The machine learning unit (15) changes each connection load of a neural network (16) from an output layer side to an input layer side according to the loss function Loss.

An information processing method includes acquiring a first prediction result by inputting evaluation data to a first model; determining an anomaly in the first prediction result based on the first prediction result and reference information; acquiring a second model based on the determination result; acquiring a second prediction result by inputting the evaluation data to the second model; determining an anomaly in the second prediction result based on the second prediction result and the reference information; acquiring a third model based on the determination result; acquiring a third prediction result by inputting the evaluation data to the third model; determining an anomaly in the third prediction result based on the third prediction result and the reference information; and if the anomaly in the third prediction result is recognized as being identical to the anomaly in the first prediction result, outputting information about a training limit of the first model.