# SSD: Towards Better Text-Image Consistency Metric in Text-to-Image Generation

arXiv: https://arxiv.org/abs/2210.15235 · HTML: https://mlsanity.com/paper/2210.15235/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 37 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Builds on (most cited first, 27 of 27)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [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)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [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)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [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)
- [MirrorGAN: Learning Text-to-image Generation by Redescription](https://mlsanity.com/paper/1903.05854/) (2019)
- [StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2108.00946/) (2021)
- [Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis](https://mlsanity.com/paper/1801.05091/) (2018)
- [Semantic Object Accuracy for Generative Text-to-Image Synthesis](https://mlsanity.com/paper/1910.13321/) (2019)
- [CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP](https://mlsanity.com/paper/2203.00386/) (2022)
- [DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis](https://mlsanity.com/paper/2108.12141/) (2021)
- [Conditional Frechet Inception Distance](https://mlsanity.com/paper/2103.11521/) (2021)
- [DTGAN: Dual Attention Generative Adversarial Networks for Text-to-Image Generation](https://mlsanity.com/paper/2011.02709/) (2020)
- [Realistic Image Generation using Region-phrase Attention](https://mlsanity.com/paper/1902.05395/) (2019)
- [SegAttnGAN: Text to Image Generation with Segmentation Attention](https://mlsanity.com/paper/2005.12444/) (2020)
- [Multi-Tailed, Multi-Headed, Spatial Dynamic Memory refined Text-to-Image Synthesis](https://mlsanity.com/paper/2110.08143/) (2021)

## Built on by (most cited first, 2 of 2)

- [Consistency in Language Models: Current Landscape, Challenges, and Future Directions](https://mlsanity.com/paper/2505.00268/) (2025)
- [Semantic Approach to Quantifying the Consistency of Diffusion Model Image Generation](https://mlsanity.com/paper/2404.08799/) (2024)

## Abstract (arXiv)

Generating consistent and high-quality images from given texts is essential for visual-language understanding. Although impressive results have been achieved in generating high-quality images, text-image consistency is still a major concern in existing GAN-based methods. Particularly, the most popular metric R-precision may not accurately reflect the text-image consistency, often resulting in very misleading semantics in the generated images. Albeit its significance, how to design a better text-image consistency metric surprisingly remains under-explored in the community. In this paper, we make a further step forward to develop a novel CLIP-based metric termed as Semantic Similarity Distance (SSD), which is both theoretically founded from a distributional viewpoint and empirically verified on benchmark datasets. Benefiting from the proposed metric, we further design the Parallel Deep Fusion Generative Adversarial Networks (PDF-GAN) that aims at improving text-image consistency by fusing semantic information at different granularities and capturing accurate semantics. Equipped with two novel plug-and-play components: Hard-Negative Sentence Constructor and Semantic Projection, the proposed PDF-GAN can mitigate inconsistent semantics and bridge the text-image semantic gap. A series of experiments show that, as opposed to current state-of-the-art methods, our PDF-GAN can lead to significantly better text-image consistency while maintaining decent image quality on the CUB and COCO datasets.