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

arXiv: https://arxiv.org/abs/2107.13516 · HTML: https://mlsanity.com/paper/2107.13516/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 76 references that are in the map.
- First posted on arXiv 28 Jul 2021.

## Builds on (most cited first, 30 of 44)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [Towards Principled Methods for Training Generative Adversarial Networks](https://mlsanity.com/paper/1701.04862/) (2017)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [Unlabeled Samples Generated by GAN Improve the Person Re-identification Baseline in vitro](https://mlsanity.com/paper/1701.07717/) (2017)
- [Cross-Modal Contrastive Learning for Text-to-Image Generation](https://mlsanity.com/paper/2101.04702/) (2021)
- [The relativistic discriminator: a key element missing from standard GAN](https://mlsanity.com/paper/1807.00734/) (2018)
- [StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1710.10916/) (2017)
- [Joint Discriminative and Generative Learning for Person Re-identification](https://mlsanity.com/paper/1904.07223/) (2019)
- [StoryGAN: A Sequential Conditional GAN for Story Visualization](https://mlsanity.com/paper/1812.02784/) (2018)
- [Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis](https://mlsanity.com/paper/1903.05628/) (2019)
- [Object-driven Text-to-Image Synthesis via Adversarial Training](https://mlsanity.com/paper/1902.10740/) (2019)
- [Learning What and Where to Draw](https://mlsanity.com/paper/1610.02454/) (2016)
- [Variational Transformer Networks for Layout Generation](https://mlsanity.com/paper/2104.02416/) (2021)
- [Photographic Text-to-Image Synthesis with a Hierarchically-nested Adversarial Network](https://mlsanity.com/paper/1802.09178/) (2018)
- [Semantics Disentangling for Text-to-Image Generation](https://mlsanity.com/paper/1904.01480/) (2019)
- [ARGAN: Attentive Recurrent Generative Adversarial Network for Shadow Detection and Removal](https://mlsanity.com/paper/1908.01323/) (2019)
- [Very Long Natural Scenery Image Prediction by Outpainting](https://mlsanity.com/paper/1912.12688/) (2019)
- [A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization](https://mlsanity.com/paper/2101.00545/) (2021)
- [Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.04357/) (2016)

## Built on by (most cited first, 10 of 10)

- [A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction](https://mlsanity.com/paper/2108.06852/) (2021)
- [MSR-GCN: Multi-Scale Residual Graph Convolution Networks for Human Motion Prediction](https://mlsanity.com/paper/2108.07152/) (2021)
- [Dual Graph Convolutional Networks with Transformer and Curriculum Learning for Image Captioning](https://mlsanity.com/paper/2108.02366/) (2021)
- [Luminance Attentive Networks for HDR Image and Panorama Reconstruction](https://mlsanity.com/paper/2109.06688/) (2021)
- [Diversity from Human Feedback](https://mlsanity.com/paper/2310.06648/) (2023)
- [Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation](https://mlsanity.com/paper/2510.22107/) (2025)
- [Fine-Grained Image Generation from Bangla Text Description using Attentional Generative Adversarial Network](https://mlsanity.com/paper/2109.11749/) (2021)
- [Common Knowledge Learning for Generating Transferable Adversarial Examples](https://mlsanity.com/paper/2307.00274/) (2023)
- [Dynamic Double Space Tower](https://mlsanity.com/paper/2506.11394/) (2025)
- [Two-flow Feedback Multi-scale Progressive Generative Adversarial Network](https://mlsanity.com/paper/2508.16089/) (2025)

## 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.