mlsanityData to 7 Oct 2026

Few-Shot Diffusion Models

arXiv 2205.15463 ↗First posted 30 May 2022cs.CV cs.LG stat.MLcited by 37

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Denoising diffusion probabilistic models (DDPM) are powerful hierarchical latent variable models with remarkable sample generation quality and training stability. These properties can be attributed to parameter sharing in the generative hierarchy, as well as a parameter-free diffusion-based inference procedure. In this paper, we present Few-Shot Diffusion Models (FSDM), a framework for few-shot generation leveraging conditional DDPMs. FSDMs are trained to adapt the generative process conditioned on a small set of images from a given class by aggregating image patch information using a set-based Vision Transformer (ViT). At test time, the model is able to generate samples from previously unseen classes conditioned on as few as 5 samples from that class. We empirically show that FSDM can perform few-shot generation and transfer to new datasets. We benchmark variants of our method on complex vision datasets for few-shot learning and compare to unconditional and conditional DDPM baselines. Additionally, we show how conditioning the model on patch-based input set information improves training convergence.

Key facts. Cited by 37 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 95 of its 124 references that are in the map. First posted on arXiv 30 May 2022.

Builds on

95 of 124 references.

Closest ancestors · 19

Same direction, newest first

  1. 2022Subspace Diffusion Generative Models3 May
  2. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  3. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents2 Jan
  4. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  5. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representation30 Nov
  6. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  7. 2021Structured Denoising Diffusion Models in Discrete State-Spaces7 Jul
  8. 2021Variational Diffusion Models1 Jul
  9. 2021Score-based Generative Modeling in Latent Space10 Jun
  10. 2021Learning to Efficiently Sample from Diffusion Probabilistic Models7 Jun
  11. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matching5 Jun
  12. 2021On Fast Sampling of Diffusion Probabilistic Models31 May
7 more
  1. 2021Cascaded Diffusion Models for High Fidelity Image Generation30 May
  2. 2021Gotta Go Fast When Generating Data with Score-Based Models28 May
  3. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  4. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  6. 2020Denoising Diffusion Implicit Models6 Oct
  7. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 76

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  6. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  7. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  8. 2017Graph Attention Networkscited by 8,854
  9. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  10. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  11. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  12. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
38 more
  1. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  2. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  8. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  10. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  11. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  12. 2022Video Diffusion Modelscited by 2,280
  13. 2016Matching Networks for One Shot Learningcited by 2,246
  14. 2015Variational Inference with Normalizing Flowscited by 2,161
  15. 2016Density estimation using Real NVPcited by 2,029
  16. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  17. 2017Deep Setscited by 1,394
  18. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
  19. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  20. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  21. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  22. 2019An Introduction to Variational Autoencoderscited by 997
  23. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  24. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  25. 2016Pixel Recurrent Neural Networkscited by 814
  26. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 734
  27. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  28. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  29. 2016Learning to learn by gradient descent by gradient descentcited by 616
  30. 2021Argmax Flows and Multinomial Diffusion: Learning Categorical Distributionscited by 566
  31. 2022GeoDiff: a Geometric Diffusion Model for Molecular Conformation Generationcited by 511
  32. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  33. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  34. 2018Conditional Neural Processescited by 421
  35. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  36. 2018Neural Processescited by 307
  37. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  38. 2021DeepViT: Towards Deeper Vision Transformercited by 288

50 most cited of 76 All 76 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 6; 2023: 19; 2024: 8; 2025: 2; 2026: 2.

37 papers.

Sort:

By area:

  1. 2022Diffusion Models in Vision: A Surveycited by 1,008
  2. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Modelscited by 297
  3. 2022A Survey on Generative Diffusion Modelcited by 238
  4. 2023PTQD: Accurate Post-Training Quantization for Diffusion Modelscited by 167
  5. 2023On the Design Fundamentals of Diffusion Models: A Surveycited by 59
  6. 2023Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generationcited by 51
  7. 2022Efficient Diffusion Models for Vision: A Surveycited by 50
  8. 2023Class-Balancing Diffusion Modelscited by 47
  9. 2022Self-Guided Diffusion Modelscited by 36
  10. 2024Group Diffusion Transformers are Unsupervised Multitask Learnerscited by 22
  11. 2022Few-shot Image Generation with Diffusion Modelscited by 21
  12. 2023Diffusion Model for Dense Matchingcited by 21
25 more
  1. 2022ADIR: Adaptive Diffusion for Image Reconstructioncited by 20
  2. 2023A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shotcited by 19
  3. 2024DiffusionPen: Towards Controlling the Style of Handwritten Text Generationcited by 16
  4. 2023Diffusion Models in Bioinformatics: A New Wave of Deep Learning Revolution in Actioncited by 15
  5. 2023DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Datacited by 15
  6. 2023Data Augmentation for Seizure Prediction with Generative Diffusion Modelcited by 13
  7. 2023Diffusion Models as Artists: Are we Closing the Gap between Humans and Machines?cited by 10
  8. 2023Diffusing the Optimal Topology: A Generative Optimization Approachcited by 9
  9. 2023Image Synthesis under Limited Data: A Survey and Taxonomycited by 9
  10. 2023EEG Synthetic Data Generation Using Probabilistic Diffusion Modelscited by 8
  11. 2025From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Modelscited by 7
  12. 2023UDPM: Upsampling Diffusion Probabilistic Modelscited by 5
  13. 2025Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learningcited by 5
  14. 2023Improving the Effectiveness of Deep Generative Datacited by 4
  15. 2023Learning to Reconstruct Accelerated MRI Through K-space Cold Diffusion without Noisecited by 4
  16. 2024Enforcing Conditional Independence for Fair Representation Learning and Causal Image Generationcited by 4
  17. 2024Diffusion-Refined VQA Annotations for Semi-Supervised Gaze Followingcited by 4
  18. 2023On quantifying and improving realism of images generated with diffusioncited by 3
  19. 2024DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognitioncited by 3
  20. 2024Style-Extracting Diffusion Models for Semi-Supervised Histopathology Segmentationcited by 3
  21. 2024Latent Representation Matters: Human-like Sketches in One-shot Drawing Taskscited by 3
  22. 2023Improving Denoising Diffusion Probabilistic Models via Exploiting Shared Representationscited by 1
  23. 2024Conditional Diffusion on Web-Scale Image Pairs leads to Diverse Image Variationscited by 0
  24. 2026Support-Conditioned Flow Matching Is Kernel Smoothingcited by 0
  25. 2026Semi-Supervised Conditional Diffusion via Label Augmentationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Diffusion Models in Low-Level Vision: A Survey
  2. 2022f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
  3. 2023Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision
  4. 2024Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolations
  5. 2022Representation Learning with Diffusion Models
  6. 2023Diffusion Models Without Attention
  7. 2024Conditional Image Synthesis with Diffusion Models: A Survey
  8. 2026Improved Distributional Diffusion Models