Generative Adversarial Networks

Evaluation of Deep Learning-based Super-resolution Methods for Enhanced Facial Identification Accuracy

This paper presents a comparative analysis of modern super-resolution (SR) methods for improving the accuracy of face recognition in video surveillance systems. The low quality of images obtained from surveillance cameras is a significant obstacle to effective person identification, making the use of SR methods particularly relevant.

Building and Optimizing Lightweight Generative Adversarial Neural Networks to Enhance Video Quality in the Client Devices Using Webgpu

The paper considers problems for the tasks of improving the quality of digital video images for cloud environments, as well as on the client side using generative adversarial neural networks (GANs) adapted for work in the browser. A method is proposed that uses WebGPU for accelerated execution of convolutional calculations, which allows to increase the resolution and improve the quality of low-quality video in real time without significant load on servers.

Architecture and Formal-mathematical Justification of Generative Adversarial Networks

The purpose of the work is to analyze the features of generative adversarial networks. The object of research is the process of machine learning algorithmization. The subject of the research is mathematical methods used in the generation of semantically related text. This article explores the architecture and mathematical justification of such a type of generative models as generative adversarial networks. Generative adversarial networks are a powerful tool in the field of artificial intelligence, capable of generating realistic data, including photos, videos, sounds, etc.