Generative Adversarial Networks (GAN) has changed the way we observe deep learning field. Up until that point, generative algorithms were a one-side ally, and the engineers were focused more on regression and classification tasks. Different approaches and applications were used for generating data. However, Ian Goodfellow presented GAN back in 2014 and shook up the entire field. Little did he knew the idea that he got while drinking with his friends would make him famous (well, science famous, not Rihanna famous).
Generative Adversarial Networks have been crucial in the developments made in unsupervised learning in recent times. Exemplars of image synthesis from text or other images, these networks have shown remarkable improvements over conventional methods in terms of performance. Trained on the adversarial training philosophy, these networks aim to estimate the potential distribution from the real data and then use this as input to generate the synthetic data. Based on this fundamental principle, several frameworks can be generated that are paragon implementations in several real-life applications such as art synthesis, generation of high resolution outputs and synthesis of images from human drawn sketches, to name a few. While theoretically GANs present better results and prove to be an improvement over conventional methods in many factors, the implementation of these frameworks for dedicated applications remains a challenge. This study explores and presents a taxonomy of these frameworks and their use in various image to image synthesis and text to image synthesis applications. The basic GANs, as well as a variety of different niche frameworks, are critically analyzed. The advantages of GANs for image generation over conventional methods as well their disadvantages amongst other frameworks are presented. The future applications of GANs in industries such as healthcare, art and entertainment are also discussed.
GANs (Generative Adversarial Networks) are a class of models where images are translated from one distribution to another. GANs are helpful in various use-cases, for example: enhancing image quality, photograph editing, image-to-image translation, clothing translation, etc. Nowadays, many retailers, fashion industries, media, etc. are making use of GANs to improve their business and relying on algorithms to do the task. There are many forms of GAN available serving different purposes, but in this article, we will focus on CycleGAN. Here we will see its working and implementation in PyTorch. CycleGAN learns the mapping of an image from source X to a target domain Y. Assume you have an aerial image of a city and want to convert in google maps image or the landscape image into a segmented image, but you don't have the paired images available, then there is GAN for you.
Deconvolution microscopy has been extensively used to improve the resolution of the widefield fluorescent microscopy. Conventional approaches, which usually require the point spread function (PSF) measurement or blind estimation, are however computationally expensive. Recently, CNN based approaches have been explored as a fast and high performance alternative. In this paper, we present a novel unsupervised deep neural network for blind deconvolution based on cycle consistency and PSF modeling layers. In contrast to the recent CNN approaches for similar problem, the explicit PSF modeling layers improve the robustness of the algorithm. Experimental results confirm the efficacy of the algorithm.