mlsanityData to 14 Oct 2026

Unsupervised Compositional Concepts Discovery with Text-to-Image Generative Models

arXiv 2306.05357 ↗First posted 8 Jun 2023cs.CV cs.AI cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

Text-to-image generative models have enabled high-resolution image synthesis across different domains, but require users to specify the content they wish to generate. In this paper, we consider the inverse problem -- given a collection of different images, can we discover the generative concepts that represent each image? We present an unsupervised approach to discover generative concepts from a collection of images, disentangling different art styles in paintings, objects, and lighting from kitchen scenes, and discovering image classes given ImageNet images. We show how such generative concepts can accurately represent the content of images, be recombined and composed to generate new artistic and hybrid images, and be further used as a representation for downstream classification tasks.

Key facts. Cited by 36 papers in the map (data through 14 Oct 2026). Builds on 45 of its 56 references that are in the map. First posted on arXiv 8 Jun 2023.

Builds on

45 of 56 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,355
  9. 2022Classifier-Free Diffusion Guidancecited by 5,847
  10. 2022Generative Adversarial Networkscited by 5,627
  11. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  12. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,614
33 more
  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  2. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  3. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  4. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  5. 2015Variational Inference with Normalizing Flowscited by 2,170
  6. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  7. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,106
  8. 2020Object-Centric Learning with Slot Attentioncited by 876
  9. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 702
  10. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 695
  11. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 624
  12. 2020GANSpace: Discovering Interpretable GAN Controlscited by 614
  13. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 392
  14. 2022Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesiscited by 388
  15. 2020StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generationcited by 332
  16. 2023Composer: Creative and Controllable Image Synthesis with Composable Conditionscited by 304
  17. 2019On the "steerability" of generative adversarial networkscited by 248
  18. 2022What the DAAM: Interpreting Stable Diffusion Using Cross Attentioncited by 236
  19. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcited by 220
  20. 2022Uncovering the Disentanglement Capability in Text-to-Image Diffusion Modelscited by 116
  21. 2023Collaborative Diffusion for Multi-Modal Face Generation and Editingcited by 116
  22. 2022Benchmarking Spatial Relationships in Text-to-Image Generationcited by 97
  23. 2023Compositional Text-to-Image Synthesis with Attention Map Control of Diffusion Modelscited by 83
  24. 2021Learning to Compose Visual Relationscited by 72
  25. 2021Unsupervised Learning of Compositional Energy Conceptscited by 71
  26. 2021Controllable and Compositional Generation with Latent-Space Energy-Based Modelscited by 64
  27. 2022MagicMix: Semantic Mixing with Diffusion Modelscited by 63
  28. 2022Composing Ensembles of Pre-trained Models via Iterative Consensuscited by 28
  29. 2020Unsupervised Discovery of 3D Physical Objects from Videocited by 27
  30. 2022The Stable Artist: Steering Semantics in Diffusion Latent Spacecited by 23
  31. 2023Attribute-Centric Compositional Text-to-Image Generationcited by 19
  32. 2023Learning Disentangled Prompts for Compositional Image Synthesiscited by 8
  33. 2023Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling Methodscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 7; 2024: 13; 2025: 8; 2026: 8.

36 papers.

Sort:

By area:

  1. 2024Multi-LoRA Composition for Image Generationcited by 80
  2. 2023Diffusion Model is Secretly a Training-free Open Vocabulary Semantic Segmentercited by 76
  3. 2023NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Modelscited by 47
  4. 2024Compositional Generative Modeling: A Single Model is Not All You Needcited by 41
  5. 2023Interpretable Diffusion via Information Decompositioncited by 37
  6. 2024Emergence of Hidden Capabilities: Exploring Learning Dynamics in Concept Spacecited by 35
  7. 2024Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretationscited by 33
  8. 2023Compositional Sculpting of Iterative Generative Processescited by 27
  9. 2025SliderSpace: Decomposing the Visual Capabilities of Diffusion Modelscited by 26
  10. 2023CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decodingcited by 20
  11. 2024Stylus: Automatic Adapter Selection for Diffusion Modelscited by 18
  12. 2024Learning Discrete Concepts in Latent Hierarchical Modelscited by 17
24 more
  1. 2024ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extractioncited by 16
  2. 2023Language-Informed Visual Concept Learningcited by 12
  3. 2024Compositional Image Decomposition with Diffusion Modelscited by 12
  4. 2024Compositional Video Generation as Flow Equalizationcited by 12
  5. 2023Denoising Heat-inspired Diffusion with Insulators for Collision Free Motion Planningcited by 8
  6. 2024Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Modelscited by 6
  7. 2025Flexible Multitask Learning with Factorized Diffusion Policycited by 5
  8. 2024Do Diffusion Models Learn Semantically Meaningful and Efficient Representations?cited by 4
  9. 2024Interpretable Measures of Conceptual Similarity by Complexity-Constrained Descriptive Auto-Encodingcited by 4
  10. 2024Few-Shot Task Learning through Inverse Generative Modelingcited by 4
  11. 2025Harnessing Caption Detailness for Data-Efficient Text-to-Image Generationcited by 4
  12. 2025Compositional Scene Understanding through Inverse Generative Modelingcited by 3
  13. 2025LoRAverse: A Submodular Framework to Retrieve Diverse Adapters for Diffusion Modelscited by 3
  14. 2026ELROND: Exploring and decomposing intrinsic capabilities of diffusion modelscited by 2
  15. 2025Enhancing Zero-Shot Image Recognition in Vision-Language Models through Human-like Concept Guidancecited by 1
  16. 2025DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoningcited by 1
  17. 2026SEDGE: Structural Extrapolated Data Generationcited by 1
  18. 2026Long-Text-to-Image Generation via Compositional Prompt Decompositioncited by 1
  19. 2026Test-Time Compositional Generalization in Diffusion Models via Concept Discoverycited by 1
  20. 2025DeMoGen: Towards Decompositional Human Motion Generation with Energy-Based Diffusion Modelscited by 0
  21. 2026Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognitioncited by 0
  22. 2026Intrinsic Concept Extraction Based on Compositional Interpretabilitycited by 0
  23. 2026From Static Analysis to Audience Dissemination: A Training-Free Multimodal Controversy Detection Multi-Agent Frameworkcited by 0
  24. 2026Medical AI Encodes a "Feeling of Error": Verifying Cancer Segmentation via Internal Conceptscited by 0