Text to Image Synthesis in Generative Adversarial Networks

Apply

Text to Image Synthesis in Generative Adversarial Networks

Journal Title: International Journal of engineering Research and Applications - Year 2019, Vol 9, Issue 1

Abstract

One of the core applications of conditional generative models is to generate images from text (natural languages). In addition to running tests on our capabilities of conditional modeling, dimensional distribution at the high level; synthesis involving text to an image has numerous practical applications. Some of the applications include the creation of machine-aided content and editing photos. In the past, huge strides of progress in generative adversarial neural nets have been made. Text to image synthesis is among one of the most interesting discoveries made in the artificial intelligence field of our century. In the year 2016, the generative adversarial network for text to image synthesis was not able to generate accurate and clear images. With the advancement made in technology and adjustments to the model, it’s now possible to generate clear and almost fully accurate images based on the description provided. Visualizing a scene given a detailed description is an undertaking that human beings do with less effort involved -nonetheless, it is a complex task that requires a combination of various concepts specified in natural so as to compare to how they look in real life. In this paper, we study previous work on image synthesis from text descriptions following the advances in generative adversarial networks (GANs), and experiment with better training techniques like feature matching, smooth labeling, and mini-batch discrimination.

Authors and Affiliations

Afreen Bhumgara, Anand Pitale

Keywords

convolutional neural networks GAN generative adversarial networks learning (artificial intelligence) machine learning natural language processing neural nets object detection text-to-image translation

EP ID EP445282
DOI 10.9790/9622- 0901020914.
Views 153
Downloads 0