Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

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

Hongchen Tan, Xiuping Liu, Baocai Yin

    IEEE Transactions on Neural Networks and Learning Systems
    |April 20, 2022
    PubMed
    Summary
    This summary is machine-generated.

    Related Concept Videos

    You might also read

    Related Articles

    Articles linked to this work by shared authors, journal, and citation graph.

    Sort by
    Same author

    Visual-Textual Information-Driven Tactile Data Generation Method.

    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026
    Same author

    Human-Like Multimodal Fake News Detection via Reflective Summarization and Large-Small Model Collaboration.

    IEEE transactions on neural networks and learning systems·2026
    Same author

    Hybrid graph attention learning with pseudo-label guided adaptive evolution.

    Neural networks : the official journal of the International Neural Network Society·2026
    Same author

    Attribute-Topology Cross-Frequency Aligned Graph Neural Networks for Homophilic and Heterophilic Graphs in Node Classification.

    IEEE transactions on neural networks and learning systems·2026
    Same author

    KSIQA: A Knowledge-Sharing Model for No-Reference Image Quality Assessment.

    IEEE transactions on neural networks and learning systems·2026
    Same author

    Multimodal Knowledge Graph Completion by Cross-Modal Interaction With Similarity Enhancing and Difference Embracing.

    IEEE transactions on neural networks and learning systems·2025
    Same journal

    Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    A Survey on Human-Centric Voice-Face Multimodal Learning.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

    IEEE transactions on neural networks and learning systems·2026
    Same journal

    FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

    IEEE transactions on neural networks and learning systems·2026
    See all related articles

    This study introduces Distribution Regularization Generative Adversarial Network (DR-GAN), a novel text-to-image model. DR-GAN enhances image generation by improving distribution learning with new semantic and normalization modules.

    Area of Science:

    • Artificial Intelligence
    • Computer Vision
    • Machine Learning

    Background:

    • Text-to-image generation models aim to synthesize realistic images from textual descriptions.
    • Existing models face challenges in accurately capturing semantic details and maintaining image quality.
    • Improved distribution learning is crucial for enhancing the performance of generative models.

    Purpose of the Study:

    • To introduce a novel text-to-image generation model, Distribution Regularization Generative Adversarial Network (DR-GAN).
    • To improve the quality and semantic accuracy of generated images through enhanced distribution learning.
    • To present new modules for semantic disentanglement and distribution normalization within the generative framework.

    Main Methods:

    • Developed DR-GAN incorporating a Semantic Disentangling Module (SDM) and a Distribution Normalization Module (DNM).

    Related Experiment Videos

  • SDM utilizes a spatial self-attention mechanism and a semantic disentangling loss for distilling key semantic information.
  • DNM employs a variational auto-encoder and a distribution adversarial loss for normalizing latent image distributions and improving discrimination.

    • Main Results:

    • DR-GAN demonstrated competitive performance on text-to-image generation tasks across two public datasets.
    • The novel modules (SDM and DNM) effectively contributed to improved image generation quality and semantic fidelity.
    • Experimental results validate the efficacy of the proposed distribution regularization approach.

    Conclusions:

    • DR-GAN offers a significant advancement in text-to-image synthesis by leveraging improved distribution learning.
    • The integration of SDM and DNM provides a robust framework for generating high-quality, semantically accurate images from text.
    • The model's performance suggests a promising direction for future research in generative adversarial networks for image synthesis.