Fine-Grained Image Generation from Bangla Text Description using Attentional Generative Adversarial Network

TL;DR

This paper introduces Bangla AttnGAN, a novel multi-stage generative adversarial network that produces high-resolution, fine-grained images from Bangla text descriptions, focusing on relevant words and details.

Contribution

The work is the first to generate fine-grained images from Bangla text using attentional GAN, addressing language complexity and resource scarcity.

Findings

Achieved better inception score on CUB dataset

First to generate images from Bangla text

Focused on relevant words for detailed image synthesis

Abstract

Generating fine-grained, realistic images from text has many applications in the visual and semantic realm. Considering that, we propose Bangla Attentional Generative Adversarial Network (AttnGAN) that allows intensified, multi-stage processing for high-resolution Bangla text-to-image generation. Our model can integrate the most specific details at different sub-regions of the image. We distinctively concentrate on the relevant words in the natural language description. This framework has achieved a better inception score on the CUB dataset. For the first time, a fine-grained image is generated from Bangla text using attentional GAN. Bangla has achieved 7th position among 100 most spoken languages. This inspires us to explicitly focus on this language, which will ensure the inevitable need of many people. Moreover, Bangla has a more complex syntactic structure and less natural language processing resource that validates our work more.