mlsanityData to 7 Oct 2026

Semantic Object Accuracy for Generative Text-to-Image Synthesis

arXiv 1910.13321 ↗First posted 29 Oct 2019cs.CV cs.LG cs.NEcited by 89

Not on the map. Why?

Cited by 21 in Diffusion models, but placed by its own abstract, which didn’t fit.

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.

Key facts. Cited by 89 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Oct 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 26; 2023: 32; 2024: 7; 2025: 6; 2026: 2.

89 papers.

Sort:

By area:

  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  2. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  3. 2023GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignmentcited by 946
  4. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  5. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 416
  6. 2021Cross-Modal Contrastive Learning for Text-to-Image Generationcited by 259
  7. 2022DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Modelscited by 230
  8. 2022SpaText: Spatio-Textual Representation for Controllable Image Generationcited by 217
  9. 2023Grounded Text-to-Image Synthesis with Attention Refocusingcited by 163
  10. 2023Dense Text-to-Image Generation with Attention Modulationcited by 162
  11. 2023Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generationcited by 159
  12. 2021LAFITE: Towards Language-Free Training for Text-to-Image Generationcited by 126
38 more
  1. 2022Benchmarking Spatial Relationships in Text-to-Image Generationcited by 96
  2. 2022Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesiscited by 75
  3. 2022StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuationcited by 74
  4. 2021FuseDream: Training-Free Text-to-Image Generation with Improved CLIP+GAN Space Optimizationcited by 71
  5. 2023Visual Programming for Text-to-Image Generation and Evaluationcited by 53
  6. 2021Adversarial Text-to-Image Synthesis: A Reviewcited by 52
  7. 2021Multimodal Image Synthesis and Editing: The Generative AI Eracited by 52
  8. 2022Modeling Image Composition for Complex Scene Generationcited by 43
  9. 2021Unifying Multimodal Transformer for Bi-directional Image and Text Generationcited by 41
  10. 2023SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesiscited by 41
  11. 2023A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generationcited by 40
  12. 2023TokenCompose: Text-to-Image Diffusion with Token-level Supervisioncited by 40
  13. 2023Highly Personalized Text Embedding for Image Manipulation by Stable Diffusioncited by 39
  14. 2022Mutual Information Divergence: A Unified Metric for Multimodal Generative Modelscited by 35
  15. 2024Consistency-diversity-realism Pareto fronts of conditional image generative modelscited by 35
  16. 2022StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesiscited by 33
  17. 2023Gradient-Free Textual Inversioncited by 28
  18. 2023DiagrammerGPT: Generating Open-Domain, Open-Platform Diagrams via LLM Planningcited by 28
  19. 2022Word-Level Fine-Grained Story Visualizationcited by 22
  20. 2025NarrLV: Towards a Comprehensive Narrative-Centric Evaluation for Long Video Generationcited by 21
  21. 2023TIAM -- A Metric for Evaluating Alignment in Text-to-Image Generationcited by 18
  22. 2023Mismatch Quest: Visual and Textual Feedback for Image-Text Misalignmentcited by 18
  23. 2021GUIGAN: Learning to Generate GUI Designs Using Generative Adversarial Networkscited by 17
  24. 2024A Survey on Quality Metrics for Text-to-Image Generationcited by 17
  25. 2022ARMANI: Part-level Garment-Text Alignment for Unified Cross-Modal Fashion Designcited by 16
  26. 2023MagicFusion: Boosting Text-to-Image Generation Performance by Fusing Diffusion Modelscited by 16
  27. 2024RealCustom++: Representing Images as Real Textual Word for Real-Time Customizationcited by 16
  28. 2023DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Datacited by 15
  29. 2021TISE: Bag of Metrics for Text-to-Image Synthesis Evaluationcited by 13
  30. 2022DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generationcited by 13
  31. 2022Lafite2: Few-shot Text-to-Image Generationcited by 13
  32. 2023Diagnostic Benchmark and Iterative Inpainting for Layout-Guided Image Generationcited by 13
  33. 2023AI-Generated Images as Data Source: The Dawn of Synthetic Eracited by 13
  34. 2021AttrLostGAN: Attribute Controlled Image Synthesis from Reconfigurable Layout and Stylecited by 11
  35. 2023Learning to Generate Semantic Layouts for Higher Text-Image Correspondence in Text-to-Image Synthesiscited by 11
  36. 2022DR-GAN: Distribution Regularization for Text-to-Image Generationcited by 10
  37. 2022Memory-Driven Text-to-Image Generationcited by 10
  38. 2023Food-500 Cap: A Fine-Grained Food Caption Benchmark for Evaluating Vision-Language Modelscited by 10

50 most cited of 89 All 89 (JSON)