# Improving Text-to-Image Synthesis Using Contrastive Learning

arXiv: https://arxiv.org/abs/2107.02423 · HTML: https://mlsanity.com/paper/2107.02423/

## Key facts

- Cited by 62 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 49 references that are in the map.
- First posted on arXiv 6 Jul 2021.

## Builds on (most cited first, 30 of 38)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (2021)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere](https://mlsanity.com/paper/2005.10242/) (2020)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [Contrastive Multi-View Representation Learning on Graphs](https://mlsanity.com/paper/2006.05582/) (2020)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [A Theoretical Analysis of Contrastive Unsupervised Representation Learning](https://mlsanity.com/paper/1902.09229/) (2019)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Debiased Contrastive Learning](https://mlsanity.com/paper/2007.00224/) (2020)
- [Image Generation from Scene Graphs](https://mlsanity.com/paper/1804.01622/) (2018)
- [DM-GAN: Dynamic Memory Generative Adversarial Networks for Text-to-Image Synthesis](https://mlsanity.com/paper/1904.01310/) (2019)
- [Cross-Modal Contrastive Learning for Text-to-Image Generation](https://mlsanity.com/paper/2101.04702/) (2021)
- [StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1710.10916/) (2017)
- [Controllable Text-to-Image Generation](https://mlsanity.com/paper/1909.07083/) (2019)
- [MirrorGAN: Learning Text-to-image Generation by Redescription](https://mlsanity.com/paper/1903.05854/) (2019)
- [Learning Deep Structure-Preserving Image-Text Embeddings](https://mlsanity.com/paper/1511.06078/) (2015)
- [Object-driven Text-to-Image Synthesis via Adversarial Training](https://mlsanity.com/paper/1902.10740/) (2019)

## Built on by (most cited first, 30 of 62)

- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors](https://mlsanity.com/paper/2203.13131/) (2022)
- [Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models](https://mlsanity.com/paper/2302.12228/) (2023)
- [SINE: SINgle Image Editing with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2212.04489/) (2022)
- [CM3: A Causal Masked Multimodal Model of the Internet](https://mlsanity.com/paper/2201.07520/) (2022)
- [Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising](https://mlsanity.com/paper/2305.18264/) (2023)
- [LAFITE: Towards Language-Free Training for Text-to-Image Generation](https://mlsanity.com/paper/2111.13792/) (2021)
- [AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion](https://mlsanity.com/paper/2310.10123/) (2023)
- [Improving Tuning-Free Real Image Editing with Proximal Guidance](https://mlsanity.com/paper/2306.05414/) (2023)
- [A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis](https://mlsanity.com/paper/2306.14544/) (2023)
- [Multimodal Conditional Image Synthesis with Product-of-Experts GANs](https://mlsanity.com/paper/2112.05130/) (2021)
- [ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models](https://mlsanity.com/paper/2305.16225/) (2023)
- [ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model](https://mlsanity.com/paper/2207.09446/) (2022)
- [CONFORM: Contrast is All You Need For High-Fidelity Text-to-Image Diffusion Models](https://mlsanity.com/paper/2312.06059/) (2023)
- [HanDiffuser: Text-to-Image Generation With Realistic Hand Appearances](https://mlsanity.com/paper/2403.01693/) (2024)
- [Multimodal Procedural Planning via Dual Text-Image Prompting](https://mlsanity.com/paper/2305.01795/) (2023)
- [Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion](https://mlsanity.com/paper/2303.08767/) (2023)
- [The Hidden Language of Diffusion Models](https://mlsanity.com/paper/2306.00966/) (2023)
- [Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback](https://mlsanity.com/paper/2307.04749/) (2023)
- [Improving Diffusion-Based Image Synthesis with Context Prediction](https://mlsanity.com/paper/2401.02015/) (2024)
- [UPainting: Unified Text-to-Image Diffusion Generation with Cross-modal Guidance](https://mlsanity.com/paper/2210.16031/) (2022)
- [LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation](https://mlsanity.com/paper/2303.12343/) (2023)
- [Improving Compositional Text-to-image Generation with Large Vision-Language Models](https://mlsanity.com/paper/2310.06311/) (2023)
- [ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generation](https://mlsanity.com/paper/2306.00971/) (2023)

## Abstract (arXiv)

The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of words. The linguistic discrepancy between the captions of the identical image leads to the synthetic images deviating from the ground truth. To address this issue, we propose a contrastive learning approach to improve the quality and enhance the semantic consistency of synthetic images. In the pretraining stage, we utilize the contrastive learning approach to learn the consistent textual representations for the captions corresponding to the same image. Furthermore, in the following stage of GAN training, we employ the contrastive learning method to enhance the consistency between the generated images from the captions related to the same image. We evaluate our approach over two popular text-to-image synthesis models, AttnGAN and DM-GAN, on datasets CUB and COCO, respectively. Experimental results have shown that our approach can effectively improve the quality of synthetic images in terms of three metrics: IS, FID and R-precision. Especially, on the challenging COCO dataset, our approach boosts the FID signifcantly by 29.60% over AttnGAN and by 21.96% over DM-GAN.