mlsanityData to 7 Oct 2026

CRD-CGAN: Category-Consistent and Relativistic Constraints for Diverse Text-to-Image Generation

arXiv 2107.13516 ↗First posted 28 Jul 2021cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Generating photo-realistic images from a text description is a challenging problem in computer vision. Previous works have shown promising performance to generate synthetic images conditional on text by Generative Adversarial Networks (GANs). In this paper, we focus on the category-consistent and relativistic diverse constraints to optimize the diversity of synthetic images. Based on those constraints, a category-consistent and relativistic diverse conditional GAN (CRD-CGAN) is proposed to synthesize K photo-realistic images simultaneously. We use the attention loss and diversity loss to improve the sensitivity of the GAN to word attention and noises. Then, we employ the relativistic conditional loss to estimate the probability of relatively real or fake for synthetic images, which can improve the performance of basic conditional loss. Finally, we introduce a category-consistent loss to alleviate the over-category issues between K synthetic images. We evaluate our approach using the Birds-200-2011, Oxford-102 flower and MSCOCO 2014 datasets, and the extensive experiments demonstrate superiority of the proposed method in comparison with state-of-the-art methods in terms of photorealistic and diversity of the generated synthetic images.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 44 of its 76 references that are in the map. First posted on arXiv 28 Jul 2021.

Builds on

44 of 76 references.

References · 44

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2016Improved Techniques for Training GANscited by 2,938
  4. 2014Conditional Generative Adversarial Netscited by 2,152
  5. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  6. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  7. 2019StarGAN v2: Diverse Image Synthesis for Multiple Domainscited by 1,095
  8. 2016Least Squares Generative Adversarial Networkscited by 1,000
  9. 2018Self-Attention Generative Adversarial Networkscited by 809
  10. 2016Generative Adversarial Text to Image Synthesiscited by 735
  11. 2017AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networkscited by 664
  12. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
32 more
  1. 2017Towards Principled Methods for Training Generative Adversarial Networkscited by 460
  2. 2016Learning from Simulated and Unsupervised Images through Adversarial Trainingcited by 287
  3. 2017Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitrocited by 280
  4. 2021Cross-Modal Contrastive Learning for Text-to-Image Generationcited by 259
  5. 2018The relativistic discriminator: a key element missing from standard GANcited by 234
  6. 2017StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 229
  7. 2019Joint Discriminative and Generative Learning for Person Re-identificationcited by 211
  8. 2019Mode Seeking Generative Adversarial Networks for Diverse Image Synthesiscited by 138
  9. 2018StoryGAN: A Sequential Conditional GAN for Story Visualizationcited by 137
  10. 2019Object-driven Text-to-Image Synthesis via Adversarial Trainingcited by 117
  11. 2016Learning What and Where to Drawcited by 105
  12. 2021Variational Transformer Networks for Layout Generationcited by 88
  13. 2018Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Networkcited by 64
  14. 2019Semantics Disentangling for Text-to-Image Generationcited by 61
  15. 2019ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removalcited by 51
  16. 2019Very Long Natural Scenery Image Prediction by Outpaintingcited by 50
  17. 2021A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localizationcited by 45
  18. 2016Stacked Generative Adversarial Networkscited by 44
  19. 2020Text-to-Image Generation Grounded by Fine-Grained User Attentioncited by 36
  20. 2019RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removalcited by 35
  21. 2021A Two-Stage Attentive Network for Single Image Super-Resolutioncited by 20
  22. 2019CatGAN: Category-aware Generative Adversarial Networks with Hierarchical Evolutionary Learning for Category Text Generationcited by 16
  23. 2018Adversarial Learning of Semantic Relevance in Text to Image Synthesiscited by 14
  24. 2020Sketch-Guided Scenery Image Outpaintingcited by 12
  25. 2020Efficient Neural Architecture for Text-to-Image Synthesiscited by 11
  26. 2019On Relativistic f-Divergencescited by 10
  27. 2018Mixture Density Generative Adversarial Networkscited by 9
  28. 2019Stochastic Conditional Generative Networks with Basis Decompositioncited by 9
  29. 2019CPGAN: Full-Spectrum Content-Parsing Generative Adversarial Networks for Text-to-Image Synthesiscited by 9
  30. 2019Iterative and Adaptive Sampling with Spatial Attention for Black-Box Model Explanationscited by 5
  31. 2018Deep Neural Networks In Fully Connected CRF For Image Labeling With Social Network Metadatacited by 4
  32. 2020Hierarchical Modes Exploring in Generative Adversarial Networkscited by 1

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 0; 2023: 2; 2024: 0; 2025: 3.

10 papers.

  1. 2021A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Predictioncited by 129
  2. 2021MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Predictioncited by 100
  3. 2021Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioningcited by 27
  4. 2021Luminance Attentive Networks for HDR Image and Panorama Reconstructioncited by 18
  5. 2023Diversity from Human Feedbackcited by 5
  6. 2025Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generationcited by 2
  7. 2021Fine-Grained Image Generation from Bangla Text Description using Attentional Generative Adversarial Networkcited by 1
  8. 2023Common Knowledge Learning for Generating Transferable Adversarial Examplescited by 1
  9. 2025Dynamic Double Space Towercited by 0
  10. 2025Two-flow Feedback Multi-scale Progressive Generative Adversarial Networkcited by 0