The Right Losses for the Right Gains: Improving the Semantic Consistency of Deep Text-to-Image Generation with Distribution-Sensitive Losses

One of the major challenges in training deep neural networks for text-to-image generation is the significant linguistic discrepancy between ground-truth captions of each image in most popular datasets. The large difference in the choice of words in such captions results in synthesizing images that a...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-12
Main Authors: Ahmed, Mahmoud, Moussa, Omer, Ismail, Shaheen, Abdelfattah, Mohamed, Abdalla, Amr, Eid, Marwan, Eraqi, Hesham, Moustafa, Mohamed
Format: Article
Language:English
Subjects:
Artificial neural networks
Consistency
Datasets
Image enhancement
Image processing
Machine learning
Semantics
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:One of the major challenges in training deep neural networks for text-to-image generation is the significant linguistic discrepancy between ground-truth captions of each image in most popular datasets. The large difference in the choice of words in such captions results in synthesizing images that are semantically dissimilar to each other and to their ground-truth counterparts. Moreover, existing models either fail to generate the fine-grained details of the image or require a huge number of parameters that renders them inefficient for text-to-image synthesis. To fill this gap in the literature, we propose using the contrastive learning approach with a novel combination of two loss functions: fake-to-fake loss to increase the semantic consistency between generated images of the same caption, and fake-to-real loss to reduce the gap between the distributions of real images and fake ones. We test this approach on two baseline models: SSAGAN and AttnGAN (with style blocks to enhance the fine-grained details of the images.) Results show that our approach improves the qualitative results on AttnGAN with style blocks on the CUB dataset. Additionally, on the challenging COCO dataset, our approach achieves competitive results against the state-of-the-art Lafite model, outperforms the FID score of SSAGAN model by 44.
ISSN:2331-8422