mlsanityData to 7 Oct 2026

Rejection Sampling IMLE: Designing Priors for Better Few-Shot Image Synthesis

arXiv 2409.17439 ↗First posted 26 Sep 2024cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

An emerging area of research aims to learn deep generative models with limited training data. Prior generative models like GANs and diffusion models require a lot of data to perform well, and their performance degrades when they are trained on only a small amount of data. A recent technique called Implicit Maximum Likelihood Estimation (IMLE) has been adapted to the few-shot setting, achieving state-of-the-art performance. However, current IMLE-based approaches encounter challenges due to inadequate correspondence between the latent codes selected for training and those drawn during inference. This results in suboptimal test-time performance. We theoretically show a way to address this issue and propose RS-IMLE, a novel approach that changes the prior distribution used for training. This leads to substantially higher quality image generation compared to existing GAN and IMLE-based methods, as validated by comprehensive experiments conducted on nine few-shot image datasets.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 32 of its 40 references that are in the map. First posted on arXiv 26 Sep 2024.

Builds on

32 of 40 references.

References · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  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. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  7. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  8. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  10. 2016Density estimation using Real NVPcited by 2,029
  11. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  12. 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
20 more
  1. 2021Alias-Free Generative Adversarial Networkscited by 1,181
  2. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  3. 2016Conditional Image Generation with PixelCNN Decoderscited by 859
  4. 2016Pixel Recurrent Neural Networkscited by 814
  5. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  6. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
  7. 2020Differentiable Augmentation for Data-Efficient GAN Trainingcited by 361
  8. 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 261
  9. 2021Few-shot Image Generation via Cross-domain Correspondencecited by 206
  10. 2021Projected GANs Converge Fastercited by 204
  11. 2021Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesiscited by 140
  12. 2020Freeze the Discriminator: a Simple Baseline for Fine-Tuning GANscited by 132
  13. 2020Few-shot Image Generation with Elastic Weight Consolidationcited by 122
  14. 2019MineGAN: effective knowledge transfer from GANs to target domains with few imagescited by 106
  15. 2020Improved StyleGAN Embedding: Where are the Good Latents?cited by 88
  16. 2018Implicit Maximum Likelihood Estimationcited by 52
  17. 2022FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANscited by 17
  18. 2021Few-shot Image Generation with Mixup-based Distance Learningcited by 16
  19. 2022FreGAN: Exploiting Frequency Components for Training GANs under Limited Datacited by 16
  20. 2017Fast k-Nearest Neighbour Search via Prioritized DCIcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 3; 2026: 5.

8 papers.

  1. 2025IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimationcited by 13
  2. 2026WIMLE: Uncertainty-Aware World Models with IMLE for Sample-Efficient Continuous Controlcited by 3
  3. 2026Implicit Maximum Likelihood Estimation for Real-time Generative Model Predictive Controlcited by 3
  4. 2025LSRS: Latent Scale Rejection Sampling for Visual Autoregressive Modelingcited by 1
  5. 2026PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learningcited by 1
  6. 2025A Non-Adversarial Approach to Idempotent Generative Modellingcited by 0
  7. 2026One Pass Is Not Enough: Recursive Latent Refinement for Generative Modelscited by 0
  8. 2026IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policiescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026ROMS-IMLE: A Minimalist Approach to Competitive Single-Step Generative Modelling
  2. 2023How Good Are Deep Generative Models for Solving Inverse Problems?
  3. 2025Inductive Moment Matching
  4. 2021Variational Diffusion Models
  5. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation
  6. 2023Conditional Image Generation with Pretrained Generative Model
  7. 2022Image Generation with Multimodal Priors using Denoising Diffusion Probabilistic Models
  8. 2022Progressive Distillation for Fast Sampling of Diffusion Models