DR-GAN: Distribution Regularization for Text-to-Image Generation

04/17/2022
by   Hongchen Tan, et al.
0

This paper presents a new Text-to-Image generation model, named Distribution Regularization Generative Adversarial Network (DR-GAN), to generate images from text descriptions from improved distribution learning. In DR-GAN, we introduce two novel modules: a Semantic Disentangling Module (SDM) and a Distribution Normalization Module (DNM). SDM combines the spatial self-attention mechanism and a new Semantic Disentangling Loss (SDL) to help the generator distill key semantic information for the image generation. DNM uses a Variational Auto-Encoder (VAE) to normalize and denoise the image latent distribution, which can help the discriminator better distinguish synthesized images from real images. DNM also adopts a Distribution Adversarial Loss (DAL) to guide the generator to align with normalized real image distributions in the latent space. Extensive experiments on two public datasets demonstrated that our DR-GAN achieved a competitive performance in the Text-to-Image task.

READ FULL TEXT

page 1

page 2

page 3

page 5

page 6

page 8

page 12

page 13

research
08/03/2021

Cycle-Consistent Inverse GAN for Text-to-Image Synthesis

This paper investigates an open research task of text-to-image synthesis...
research
07/21/2022

SGBANet: Semantic GAN and Balanced Attention Network for Arbitrarily Oriented Scene Text Recognition

Scene text recognition is a challenging task due to the complex backgrou...
research
02/26/2018

Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network

This paper presents a novel method to deal with the challenging task of ...
research
09/03/2022

DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation

Text-to-image generation aims at generating realistic images which are s...
research
05/18/2019

Variational Hetero-Encoder Randomized Generative Adversarial Networks for Joint Image-Text Modeling

For bidirectional joint image-text modeling, we develop variational hete...
research
04/07/2019

Normalized Diversification

Generating diverse yet specific data is the goal of the generative adver...
research
06/26/2023

A Simple and Effective Baseline for Attentional Generative Adversarial Networks

Synthesising a text-to-image model of high-quality images by guiding the...

Please sign up or login with your details

Forgot password? Click here to reset