Recent Advances of Generative Adversarial Networks in Computer Vision

Abstract

The appearance of generative adversarial networks (GAN) provides a new approach and framework for computer vision. Compared with traditional machine learning algorithms, GAN works via adversarial training concept and is more powerful in both feature learning and representation. GAN also exhibits some problems, such as non-convergence, model collapse, and uncontrollability due to high degree of freedom. How to improve the theory of GAN and apply it to computer-vision-related tasks have now attracted much research efforts. In this paper, recently proposed GAN models and their applications in computer vision are systematically reviewed. In particular, we firstly survey the history and development of generative algorithms, the mechanism of GAN, its fundamental network structures, and theoretical analysis of the original GAN. Classical GAN algorithms are then compared comprehensively in terms of the mechanism, visual results of generated samples, and Frechet Inception Distance. These networks are further evaluated from network construction, performance, and applicability aspects by extensive experiments conducted over public datasets. After that, several typical applications of GAN in computer vision, including high-quality samples generation, style transfer, and image translation, are examined. Finally, some existing problems of GAN are summarized and discussed and potential future research topics are forecasted. INDEX TERMS Deep learning, generative adversarial networks (GAN), computer vision (CV), image generation, style transfer, image inpainting.

Within the Lack of Chest COVID-19 X-ray Dataset: A Novel Detection Model Based on GAN and Deep Transfer Learning

“…The discriminator tries to distinguish between real data and fake (artificially generated) data generated by the generator network as shown in Figure 2. The mission GANs models that generator network is to try fooling the discriminator network and the discriminator network tries to fight from being fooled [24][25][26][27]. Figure 2.…”

AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems

“…Sample mini-batch of bs examples {z (1) , · · · , z (bs) } from the noise prior p g (z) 11: 13: end for 14: In the generator G, output l feature maps with 256 × 256 resolution constitute a set of Ψ i . the fingerprint database will be highly similar, which will reduce the localization accuracy.…”

An affordable deep learning based solution to support pick and place robotic tasks

“…Further, the former category, deep learning, can facilitate feature extraction in the different representation of data by sampling multi-level abstractions of input data, examples include Convolutional Neural Network (CNN) [20] and Recurrent Neural Network (RNN) [22], etc. While there are other deep learning algorithms with a generative approach, such as Generative Adversarial Network (GAN) [14] and Variational Autoencoders (VAE) [24]; they build a model based on simulated observations that extracted from a probability density function [8]. Additionally, deep learning handles large scale datasets such as ImageNet with satisfactory performance [11].…”