Search

Image matching and classification methods, as well as synchronous location and mapping, are widely used on embedded and mobile devices. Their most resource-intensive part is the detection and description of the key points of the images. And if the classical methods of detecting and describing key points can be executed in real time on mobile devices, then for modern neural network methods with the best quality, such use is difficult. Thus, it is important to increase the speed of neural network models for the detection and description of key points. The subject of research is distillation as one of the methods for reducing neural network models. The aim of thestudy is to obtain a more compact model of detection and description of key points, as well as a description of the procedure for obtaining this model. A method for the distillation of neural networks for the task of detecting and describing key points was tested. The objective function and training parameters that provide the best results in the framework of the study are proposed. A new data set has been introduced for testing key point detection methods and a new quality indicator of the allocated key points and their corresponding local features. As a result of training in the described way, the new model, with the same number of parameters, showed greater accuracy in comparing key points than the original model. A new model with a significantly smaller number of parameters shows the accuracy of point matching close to the accuracy of the original model., Comment: in Russian

"Patterning" is a cognitive intervention that is unknown to psychologists, but has nevertheless been taught for half a century in nearly all kindergartens and many preschools in English-speaking countries. Patterning is the understanding that a certain rule governs the sequence of items in a series. At the simplest level, if the series has been red, tan, red, tan, red, tan, the next item should be red. More advanced patterns--"growing" geometric patterns and complex patterns of letters, numbers, and objects--have also been studied. Patterning is thought by educators to be a key cognitive ability that promotes academic achievement. However, its relative position in the hierarchy of cognitive developments is unknown. The present study showed that it is closely related to both transitivity and seriation, and that size transitivity problems best expressed the common factor that predicted patterning scores. [This article was published in "Psychology" v9 p2073-2082 2018.]