Progressive precision image classifier and method of training include storing a dataset of labeled images, training a neural network to generate a classification vector comprising a plurality of confidence values, each confidence value corresponding to a classification, validating the trained neural network, calculating fine-grained confidence thresholds for each classification, wherein each classification represents a leaf-level classification in a hierarchical classification structure, and calculating coarse-level confidence thresholds for at least one parent class in the hierarchical classification structure, wherein each parent class defines a group of at least one leaf-level classification. Each label in the training data identifies a leaf-level classification in the hierarchical classification structure, and the classification vector includes a 1xN vector of confidence values, where N represents a number of leaf-level classifications output by the trained neural network. The neural network may be implemented as a convolution neural network with a single output head.

Systems, methods, and computer-readable media are disclosed for dynamically adjusting a configuration of a pre-processor and/or a post-processor of a machine learning system. In one aspect, a machine learning system can receive raw data at a pre-processor where the pre-processor being configured to generate pre-processed data, train a machine learning model based on the pre-processed data to generate output data, process the output data at a post-processor to generate inference data, and adjust, by a controller, configuration of one or a combination of the pre-processor and the post-processor based on the inference data.

Systems, methods, and computer-readable media are disclosed for dynamically adjusting a configuration of a pre-processor and/or a post-processor of a machine learning system. In one aspect, a machine learning system can receive raw data at a pre-processor where the pre-processor being configured to generate pre-processed data, train a machine learning model based on the pre-processed data to generate output data, process the output data at a post-processor to generate inference data, and adjust, by a controller, configuration of one or a combination of the pre-processor and the post-processor based on the inference data.

A system and a method of performing face recognition may include: receiving a first facial image, depicting a first face, and a second facial image depicting a second face; applying an ML model on the first image, to produce a first representation vector, and applying the ML model on the second image to produce a second representation vector; comparing the first representation vector and the second representation vector; and associating the first face with the second face based on the comparison, where the ML model is trained to produce the representation vectors from the facial images, based on regions in the facial images that correspond to distinctiveness scores that are beneath a distinctiveness threshold.

A system and a method of performing face recognition may include: receiving a first facial image, depicting a first face, and a second facial image depicting a second face; applying an ML model on the first image, to produce a first representation vector, and applying the ML model on the second image to produce a second representation vector; comparing the first representation vector and the second representation vector; and associating the first face with the second face based on the comparison, where the ML model is trained to produce the representation vectors from the facial images, based on regions in the facial images that correspond to distinctiveness scores that are beneath a distinctiveness threshold.

A learning device is configured to comprise a learning unit, an attention part detection unit, and a data generation unit in order to enhance estimation accuracy based on a learning model with respect to various kinds of data. The learning unit executes machine learning on the basis of first learning data and generates a learning model that classifies a category of the first learning data. The attention part detection unit classifies the category of the first learning data by using the generated learning model. When performing the classification, the attention part detection unit detects, in the first learning data, a part to which the learning model pays attention. The data generation unit generates second learning data obtained by processing the attention-paid part on the basis of the proportion of the attention-paid part matching a pre-determined attention determination part to which attention should be paid.

A learning device is configured to comprise a learning unit, an attention part detection unit, and a data generation unit in order to enhance estimation accuracy based on a learning model with respect to various kinds of data. The learning unit executes machine learning on the basis of first learning data and generates a learning model that classifies a category of the first learning data. The attention part detection unit classifies the category of the first learning data by using the generated learning model. When performing the classification, the attention part detection unit detects, in the first learning data, a part to which the learning model pays attention. The data generation unit generates second learning data obtained by processing the attention-paid part on the basis of the proportion of the attention-paid part matching a pre-determined attention determination part to which attention should be paid.

A neural network model that can perform highly accurate processing on input data is provided. The neural network model includes first and second neutral networks, and the first neural network includes a first layer, a second layer, and a third layer. A feature map output from the first layer is input to the second layer and the second neural network, and a feature map output from the second neural network is input to the third layer. Given that the feature map output from the first layer when first data is input to the first neural network is a correct feature map and that the feature map output from the first layer when second data obtained by adding noise to the first data is input to the first neural network is a learning feature map, the second neural network is learned so that a feature map output from the second neural network matches the correct feature map when the learning feature map is input.

A neural network model that can perform highly accurate processing on input data is provided. The neural network model includes first and second neutral networks, and the first neural network includes a first layer, a second layer, and a third layer. A feature map output from the first layer is input to the second layer and the second neural network, and a feature map output from the second neural network is input to the third layer. Given that the feature map output from the first layer when first data is input to the first neural network is a correct feature map and that the feature map output from the first layer when second data obtained by adding noise to the first data is input to the first neural network is a learning feature map, the second neural network is learned so that a feature map output from the second neural network matches the correct feature map when the learning feature map is input.

An analysis device for visualizing an accuracy of a trained determination device includes an acquisition unit acquiring an image pair of a non-defective product image and a defective product image, an extraction unit extracting an image region of a defective part of the defective product, a generation unit generating a plurality of image regions of pseudo-defective parts, a compositing unit synthesizing each of the image regions of the plurality of pseudo-defective parts with the non-defective product image to generate a plurality of composite images having different feature quantities, an unit outputting the plurality of composite images to the determination device and acquiring a label corresponding to each of the plurality of composite images from the determination device, and a display control unit displaying an object indicating the label corresponding to each of the plurality of composite images in an array based on the feature quantities.