Синтез обучающих выборок для классификации дорожных знаков с помощью нейросетей
In this work, we research the applicability of generative adversarial neural networks for generating training samples for a traffic sign classification task. We consider generative neural networks trained using the Wasserstein metric. As a baseline method for comparison, we take image generation based on traffic sign icons. Experimental evaluation of the classifiers based on convolutional neural networks is conducted on real data, two types of synthetic data, and a combination of real and synthetic data. The experiments show that modern generative neural networks are capable of generating realistic training samples for traffic sign classification that outperform methods for generating images with icons, but are still slightly worse than real images for classifier training.
The article is devoted to the history and problems of creating interfaces. Shows the complexity and importance of effective interfaces, noted that this problem is a system of multilevel interdisciplinary. The new systems should be given serious attention to issues of human efficiency level. Man is still the leading element in determining the efficiency of any ergatic system. The main means of control in ergatic systems including computers, is the graphic manipulator (GM), with which to control the on-screen controls. Are the main styles of user interface. The most popular are GUI-interface (GUI - GraphicalUserInterface) and based on them WUI-interface (WUI-WebUserInterface). The development of equipment and technology of computer modeling led to the active introduction of virtual reality technology to ensure the inclusion of people in artificial worlds. Their main feature - full control of all the parameters of the development and the emergence of a sense of presence in people who live in these environments, which are called immersive. Technology induced environments allow a number of new, not generally applicable to the present, of interfaces using specially engineered virtual environments. Much attention is paid to creating the most advanced systems - systems contact management, which are the camera and sophisticated software. The drawbacks of modern non-contact control. Is being developed to create a contactless intelligent interface, which will allow: to control with data from a video camera, which is installed on your computer have a high noise immunity, clearly identify the user to recognize the situational environment, have an acceptable cost.
The volume contains the abstracts of the 12th International Conference "Intelligent Data Processing: Theory and Applications". The conference is organized by the Russian Academy of Sciences, the Federal Research Center "Informatics and Control" of the Russian Academy of Sciences and the Scientific and Coordination Center "Digital Methods of Data Mining". The conference has being held biennially since 1989. It is one of the most recognizable scientific forums on data mining, machine learning, pattern recognition, image analysis, signal processing, and discrete analysis. The Organizing Committee of IDP-2018 is grateful to Forecsys Co. and CFRS Co. for providing assistance in the conference preparation and execution. The conference is funded by RFBR, grant 18-07-20075. The conference website http://mmro.ru/en/.
Proceedings of the 2015 IEEE International Conference on Computer Vision
The Shape Boltzmann Machine (SBM) and its multilabel version MSBM have been recently introduced as deep generative models that capture the variations of an object shape. While being more flexible MSBM requires datasets with labeled parts of the objects for training. In the paper we present an algorithm for training MSBM using binary masks of objects and the seeds which approximately correspond to the locations of objects parts. The latter can be obtained from part-based detectors in an unsupervised manner. We derive a latent variable model and an EM-like training procedure for adjusting the weights of MSBM using a deep learning framework. We show that the model trained by our method outperforms SBM in the tasks related to binary shapes and is very close to the original MSBM in terms of quality of multilabel shapes.
This paper is concerned with stock liquidity as a factor in making capital structure decisions by managers of Russian firms. Although a big number of studies on capital structure occurred over the last few decades, stock liquidity has only recently attracted scholars’ attention as a possible driver for the choice of capital structure. Yet the existing papers are based on data from the developed capital markets. The latter differ substantially from the Russian market in terms of institutional environment and more liquid stocks. Against the background of revisions in the Russian clearing system that are expected to boost liquidity of stocks, this paper gains in currency.
The theoretic mechanisms behind the interplay of stock liquidity and capital structure are discussed in previous studies. Lower stock liquidity is associated with higher transaction costs and informational asymmetry, and thus with higher required return. Therefore it is assumed that the managers aiming at firm value maximization would prefer debt to equity financing in case if stock is not liquid enough. There are also theoretic grounds to expect an opposite impact of capital structure on stock liquidity.