# Semantic Object Accuracy for Generative Text-to-Image Synthesis

arXiv: https://arxiv.org/abs/1910.13321 · HTML: https://mlsanity.com/paper/1910.13321/

## Key facts

- Cited by 89 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2019.

## Built on by (most cited first, 30 of 89)

- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [Cross-Modal Contrastive Learning for Text-to-Image Generation](https://mlsanity.com/paper/2101.04702/) (2021)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [SpaText: Spatio-Textual Representation for Controllable Image Generation](https://mlsanity.com/paper/2211.14305/) (2022)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [Grounded Text-to-Image Synthesis with Attention Refocusing](https://mlsanity.com/paper/2306.05427/) (2023)
- [Dense Text-to-Image Generation with Attention Modulation](https://mlsanity.com/paper/2308.12964/) (2023)
- [LAFITE: Towards Language-Free Training for Text-to-Image Generation](https://mlsanity.com/paper/2111.13792/) (2021)
- [Benchmarking Spatial Relationships in Text-to-Image Generation](https://mlsanity.com/paper/2212.10015/) (2022)
- [Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesis](https://mlsanity.com/paper/2208.13753/) (2022)
- [StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation](https://mlsanity.com/paper/2209.06192/) (2022)
- [FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimization](https://mlsanity.com/paper/2112.01573/) (2021)
- [Visual Programming for Text-to-Image Generation and Evaluation](https://mlsanity.com/paper/2305.15328/) (2023)
- [Adversarial Text-to-Image Synthesis: A Review](https://mlsanity.com/paper/2101.09983/) (2021)
- [Multimodal Image Synthesis and Editing: The Generative AI Era](https://mlsanity.com/paper/2112.13592/) (2021)
- [Modeling Image Composition for Complex Scene Generation](https://mlsanity.com/paper/2206.00923/) (2022)
- [Unifying Multimodal Transformer for Bi-directional Image and Text Generation](https://mlsanity.com/paper/2110.09753/) (2021)
- [SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesis](https://mlsanity.com/paper/2304.14573/) (2023)
- [A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation](https://mlsanity.com/paper/2310.16656/) (2023)
- [TokenCompose: Text-to-Image Diffusion with Token-level Supervision](https://mlsanity.com/paper/2312.03626/) (2023)
- [Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion](https://mlsanity.com/paper/2303.08767/) (2023)
- [Consistency-diversity-realism Pareto fronts of conditional image generative models](https://mlsanity.com/paper/2406.10429/) (2024)
- [Mutual Information Divergence: A Unified Metric for Multimodal Generative Models](https://mlsanity.com/paper/2205.13445/) (2022)
- [StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis](https://mlsanity.com/paper/2203.15799/) (2022)
- [Gradient-Free Textual Inversion](https://mlsanity.com/paper/2304.05818/) (2023)
- [DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planning](https://mlsanity.com/paper/2310.12128/) (2023)

## Abstract (arXiv)

Generative adversarial networks conditioned on textual image descriptions are capable of generating realistic-looking images. However, current methods still struggle to generate images based on complex image captions from a heterogeneous domain. Furthermore, quantitatively evaluating these text-to-image models is challenging, as most evaluation metrics only judge image quality but not the conformity between the image and its caption. To address these challenges we introduce a new model that explicitly models individual objects within an image and a new evaluation metric called Semantic Object Accuracy (SOA) that specifically evaluates images given an image caption. The SOA uses a pre-trained object detector to evaluate if a generated image contains objects that are mentioned in the image caption, e.g. whether an image generated from "a car driving down the street" contains a car. We perform a user study comparing several text-to-image models and show that our SOA metric ranks the models the same way as humans, whereas other metrics such as the Inception Score do not. Our evaluation also shows that models which explicitly model objects outperform models which only model global image characteristics.