mlsanityData to 14 Oct 2026

Gender Artifacts from Art History to Text-to-Image Generation

arXiv 2606.05829 ↗First posted 4 Jun 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Artistic styles are rooted in specific socio-historical contexts that encode social hierarchies, including distinct constructions of gender. Yet in AI research, style has long been treated as a surface-level visual property: a filter of color, brushstroke, and texture applied to otherwise content-neutral scenes. We introduce the first dataset to investigate the interplay between gender representation and style in both historical and generated images. StyleGender comprises 74k images spanning 19 artistic styles, comprising art historical images with style and gender annotations, T2I-generated images under controlled style and gender prompts, and a semantically aligned set enabling direct art history-to-generation comparison. By proposing two Set Gender Artifact (SGA) metrics (PixelSGA and MaskSGA), capturing gender signals at the pixel level and in compositional structure, we show that (1) gender representation shapes visual features across artistic styles, (2) style keywords carry these patterns into T2I generation, and (3) generative models tend to amplify gender artifacts beyond what is observed in historical sources.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 43 of its 67 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

43 of 67 references.

References · 43

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  2. 2020End-to-End Object Detection with Transformerscited by 7,414
  3. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  4. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  5. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  6. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  7. 2022DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detectioncited by 1,319
  8. 2022DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Modelscited by 379
  9. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  10. 2020Large image datasets: A pyrrhic win for computer vision?cited by 237
  11. 2023Stable Bias: Analyzing Societal Representations in Diffusion Modelscited by 226
  12. 2017Neural Style Transfer: A Reviewcited by 199
31 more
  1. 2023Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Modelscited by 175
  2. 2019Towards Fairer Datasets: Filtering and Balancing the Distribution of the People Subtree in the ImageNet Hierarchycited by 156
  3. 2017CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Normscited by 96
  4. 2022How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?cited by 92
  5. 2021A Survey on Bias in Visual Datasetscited by 84
  6. 2024Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigationcited by 66
  7. 2023ITI-GEN: Inclusive Text-to-Image Generationcited by 64
  8. 2023Into the LAIONs Den: Investigating Hate in Multimodal Datasetscited by 54
  9. 2023Uncurated Image-Text Datasets: Shedding Light on Demographic Biascited by 52
  10. 2023TIBET: Identifying and Evaluating Biases in Text-to-Image Generative Modelscited by 52
  11. 2022ArtFID: Quantitative Evaluation of Neural Style Transfercited by 49
  12. 2023ControlStyle: Text-Driven Stylized Image Generation Using Diffusion Priorscited by 40
  13. 2023T2IAT: Measuring Valence and Stereotypical Biases in Text-to-Image Generationcited by 39
  14. 2022Gender Artifacts in Visual Datasetscited by 38
  15. 2022Quantifying Societal Bias Amplification in Image Captioningcited by 37
  16. 2023Stereotypes and Smut: The (Mis)representation of Non-cisgender Identities by Text-to-Image Modelscited by 27
  17. 2023A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?cited by 25
  18. 2023Stable Diffusion Exposed: Gender Bias from Prompt to Imagecited by 25
  19. 2023Multimodal Composite Association Score: Measuring Gender Bias in Generative Multimodal Modelscited by 21
  20. 2023Smiling Women Pitching Down: Auditing Representational and Presentational Gender Biases in Image Generative AIcited by 19
  21. 2024BIGbench: A Unified Benchmark for Evaluating Multi-dimensional Social Biases in Text-to-Image Modelscited by 18
  22. 2024New Job, New Gender? Measuring the Social Bias in Image Generation Modelscited by 16
  23. 2024Harm Amplification in Text-to-Image Modelscited by 15
  24. 2025OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypescited by 8
  25. 2023Analysing Gender Bias in Text-to-Image Models using Object Detectioncited by 7
  26. 2025Training-Free Style and Content Transfer by Leveraging U-Net Skip Connections in Stable Diffusioncited by 6
  27. 2025Bias Amplification in Stable Diffusion's Representation of Stigma Through Skin Tones and Their Homogeneitycited by 5
  28. 2025Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluationcited by 5
  29. 2024Civiverse: A Dataset for Analyzing User Engagement with Open-Source Text-to-Image Modelscited by 3
  30. 2024StyleForge: Enhancing Text-to-Image Synthesis for Any Artistic Styles with Dual Bindingcited by 2
  31. 2024No Annotations for Object Detection in Art through Stable Diffusioncited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026MMArt: A Multi-Perspective Multimodal Dataset for Visual Art Understandingcited by 0