mlsanityData to 7 Oct 2026

Instance-Conditioned GAN

arXiv 2109.05070 ↗First posted 10 Sep 2021cs.CV cs.LGcited by 119

Not on the map. Why?

Cited by 39 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generative Adversarial Networks (GANs) can generate near photo realistic images in narrow domains such as human faces. Yet, modeling complex distributions of datasets such as ImageNet and COCO-Stuff remains challenging in unconditional settings. In this paper, we take inspiration from kernel density estimation techniques and introduce a non-parametric approach to modeling distributions of complex datasets. We partition the data manifold into a mixture of overlapping neighborhoods described by a datapoint and its nearest neighbors, and introduce a model, called instance-conditioned GAN (IC-GAN), which learns the distribution around each datapoint. Experimental results on ImageNet and COCO-Stuff show that IC-GAN significantly improves over unconditional models and unsupervised data partitioning baselines. Moreover, we show that IC-GAN can effortlessly transfer to datasets not seen during training by simply changing the conditioning instances, and still generate realistic images. Finally, we extend IC-GAN to the class-conditional case and show semantically controllable generation and competitive quantitative results on ImageNet; while improving over BigGAN on ImageNet-LT. Code and trained models to reproduce the reported results are available at https://github.com/facebookresearch/ic_gan.

Key facts. Cited by 119 papers in the map (data through 7 Oct 2026). Builds on 53 of its 60 references that are in the map. First posted on arXiv 10 Sep 2021.

Builds on

53 of 60 references.

References · 53

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  5. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  6. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  7. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  9. 2016Improved Techniques for Training GANscited by 2,938
  10. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  11. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  12. 2017Billion-scale similarity search with GPUscited by 2,477
38 more
  1. 2016Matching Networks for One Shot Learningcited by 2,246
  2. 2017Improved Training of Wasserstein GANscited by 2,223
  3. 2014Conditional Generative Adversarial Netscited by 2,152
  4. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  5. 2019Semantic Image Synthesis with Spatially-Adaptive Normalizationcited by 1,295
  6. 2020Training Generative Adversarial Networks with Limited Datacited by 1,184
  7. 2017High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANscited by 1,176
  8. 2017Deeper, Broader and Artier Domain Generalizationcited by 983
  9. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  10. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
  11. 2018Self-Attention Generative Adversarial Networkscited by 809
  12. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
  13. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
  14. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  15. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  16. 2018Image Generation from Scene Graphscited by 324
  17. 2017Photographic Image Synthesis with Cascaded Refinement Networkscited by 223
  18. 2016Unrolled Generative Adversarial Networkscited by 208
  19. 2019The Deepfake Detection Challenge (DFDC) Preview Datasetcited by 208
  20. 2018Image Generation from Layoutcited by 105
  21. 2017PacGAN: The power of two samples in generative adversarial networkscited by 104
  22. 2019Image Synthesis From Reconfigurable Layout and Stylecited by 85
  23. 2019Specifying Object Attributes and Relations in Interactive Scene Generationcited by 76
  24. 2019Local Class-Specific and Global Image-Level Generative Adversarial Networks for Semantic-Guided Scene Generationcited by 75
  25. 2020SketchyCOCO: Image Generation from Freehand Scene Sketchescited by 67
  26. 2017Multi-Agent Diverse Generative Adversarial Networkscited by 59
  27. 2020Object-Centric Image Generation from Layoutscited by 57
  28. 2020Diverse Image Generation via Self-Conditioned GANscited by 54
  29. 2019High-Fidelity Image Generation With Fewer Labelscited by 51
  30. 2018Semi-parametric Image Synthesiscited by 50
  31. 2020Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesiscited by 49
  32. 2020Grafit: Learning fine-grained image representations with coarse labelscited by 43
  33. 2020Instance Selection for GANscited by 23
  34. 2017Logo Synthesis and Manipulation with Clustered Generative Adversarial Networkscited by 20
  35. 2018Mixture Density Generative Adversarial Networkscited by 9
  36. 2021Partition-Guided GANscited by 9
  37. 2020Self-labeled Conditional GANscited by 8
  38. 2018Mixed batches and symmetric discriminators for GAN trainingcited by 7

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 28; 2023: 44; 2024: 23; 2025: 13; 2026: 7.

119 papers.

Sort:

By area:

  1. 2022Flow Matching for Generative Modelingcited by 5,426
  2. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  3. 2022StyleGAN-XL: Scaling StyleGAN to Large Diverse Datasetscited by 489
  4. 2024Retrieval-Augmented Generation for AI-Generated Content: A Surveycited by 352
  5. 2023FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attentioncited by 313
  6. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Modelscited by 297
  7. 2023HyperDreamBooth: HyperNetworks for Fast Personalization of Text-to-Image Modelscited by 224
  8. 2021More Control for Free! Image Synthesis with Semantic Diffusion Guidancecited by 211
  9. 2023Subject-driven Text-to-Image Generation via Apprenticeship Learningcited by 210
  10. 2023Controlling Text-to-Image Diffusion by Orthogonal Finetuningcited by 207
  11. 2023Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priorscited by 156
  12. 2023Return of Unconditional Generation: A Self-supervised Representation Generation Methodcited by 95
38 more
  1. 2021Ensembling Off-the-shelf Models for GAN Trainingcited by 84
  2. 2022Frido: Feature Pyramid Diffusion for Complex Scene Image Synthesiscited by 75
  3. 2022Visual Prompt Tuning for Generative Transfer Learningcited by 75
  4. 2021High Fidelity Visualization of What Your Self-Supervised Representation Knows Aboutcited by 64
  5. 2022Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Modelscited by 63
  6. 2022Hyper-Representations as Generative Models: Sampling Unseen Neural Network Weightscited by 63
  7. 2023Unified Multi-Modal Latent Diffusion for Joint Subject and Text Conditional Image Generationcited by 60
  8. 2022Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANscited by 55
  9. 2024Diffusion Models and Representation Learning: A Surveycited by 53
  10. 2022Decoding natural image stimuli from fMRI data with a surface-based convolutional networkcited by 48
  11. 20233D generation on ImageNetcited by 47
  12. 2023Photoswap: Personalized Subject Swapping in Imagescited by 47
  13. 2023MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusioncited by 47
  14. 2022Retrieval-based Controllable Molecule Generationcited by 44
  15. 2023Sound to Visual Scene Generation by Audio-to-Visual Latent Alignmentcited by 41
  16. 2022StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesiscited by 38
  17. 2022Self-Distilled StyleGAN: Towards Generation from Internet Photoscited by 37
  18. 2023Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labelscited by 37
  19. 2023DreamTeacher: Pretraining Image Backbones with Deep Generative Modelscited by 37
  20. 2022Semi-Parametric Neural Image Synthesiscited by 36
  21. 2022Self-Guided Diffusion Modelscited by 36
  22. 2022State-of-the-Art in the Architecture, Methods and Applications of StyleGANcited by 34
  23. 2023Brain Captioning: Decoding human brain activity into images and textcited by 33
  24. 2023Feedback-guided Data Synthesis for Imbalanced Classificationcited by 33
  25. 2022FlexIT: Towards Flexible Semantic Image Translationcited by 28
  26. 2023Gradient-Free Textual Inversioncited by 28
  27. 2022Why Are Conditional Generative Models Better Than Unconditional Ones?cited by 27
  28. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  29. 2021Improving GAN Equilibrium by Raising Spatial Awarenesscited by 22
  30. 2022Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Valuescited by 21
  31. 2023Through their eyes: multi-subject Brain Decoding with simple alignment techniquescited by 21
  32. 2024DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latentscited by 20
  33. 2023ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Processcited by 19
  34. 2023Complexity Matters: Rethinking the Latent Space for Generative Modelingcited by 19
  35. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  36. 2025Highly Compressed Tokenizer Can Generate Without Trainingcited by 17
  37. 2023Meta-Personalizing Vision-Language Models to Find Named Instances in Videocited by 16
  38. 2024Towards Geographic Inclusion in the Evaluation of Text-to-Image Modelscited by 16

50 most cited of 119 All 119 (JSON)