mlsanityData to 7 Oct 2026

Score-Based Generative Classifiers

arXiv 2110.00473 ↗First posted 1 Oct 2021stat.ML cs.CV cs.LGcited by 53

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

The tremendous success of generative models in recent years raises the question whether they can also be used to perform classification. Generative models have been used as adversarially robust classifiers on simple datasets such as MNIST, but this robustness has not been observed on more complex datasets like CIFAR-10. Additionally, on natural image datasets, previous results have suggested a trade-off between the likelihood of the data and classification accuracy. In this work, we investigate score-based generative models as classifiers for natural images. We show that these models not only obtain competitive likelihood values but simultaneously achieve state-of-the-art classification accuracy for generative classifiers on CIFAR-10. Nevertheless, we find that these models are only slightly, if at all, more robust than discriminative baseline models on out-of-distribution tasks based on common image corruptions. Similarly and contrary to prior results, we find that score-based are prone to worst-case distribution shifts in the form of adversarial perturbations. Our work highlights that score-based generative models are closing the gap in classification accuracy compared to standard discriminative models. While they do not yet deliver on the promise of adversarial and out-of-domain robustness, they provide a different approach to classification that warrants further research.

Key facts. Cited by 53 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 25 of its 54 references that are in the map. First posted on arXiv 1 Oct 2021.

Builds on

25 of 54 references.

Closest ancestors · 5

Same direction, newest first

  1. 2021Variational Diffusion Models1 Jul
  2. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  3. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  5. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 20

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2018Neural Ordinary Differential Equationscited by 3,733
  6. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  7. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  8. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  9. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  10. 2015A note on the evaluation of generative modelscited by 291
  11. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  12. 2021Adversarial purification with Score-based generative modelscited by 132
8 more
  1. 2016Resnet in Resnet: Generalizing Residual Architecturescited by 110
  2. 2018Towards the first adversarially robust neural network model on MNISTcited by 104
  3. 2020Solving Linear Inverse Problems Using the Prior Implicit in a Denoisercited by 78
  4. 2017Adversarial examples for generative modelscited by 58
  5. 2018Are Generative Classifiers More Robust to Adversarial Attacks?cited by 36
  6. 2019Detecting Out-of-Distribution Inputs to Deep Generative Models Using Typicalitycited by 30
  7. 2019Understanding the Limitations of Conditional Generative Modelscited by 28
  8. 2021Defending Against Image Corruptions Through Adversarial Augmentationscited by 28

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 10; 2023: 15; 2024: 16; 2025: 11; 2026: 1.

53 papers.

Sort:

By area:

  1. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  3. 2022Diffusion Models in Vision: A Surveycited by 1,008
  4. 2023Your Diffusion Model is Secretly a Zero-Shot Classifiercited by 301
  5. 2022Diffusion Models for Medical Image Analysis: A Comprehensive Surveycited by 269
  6. 2023Editing Implicit Assumptions in Text-to-Image Diffusion Modelscited by 128
  7. 2023Denoising Diffusion Autoencoders are Unified Self-supervised Learnerscited by 128
  8. 2022Score matching enables causal discovery of nonlinear additive noise modelscited by 108
  9. 2022CARD: Classification and Regression Diffusion Modelscited by 102
  10. 2023Robust Classification via a Single Diffusion Modelcited by 79
  11. 2023Dif-Fusion: Towards High Color Fidelity in Infrared and Visible Image Fusion with Diffusion Modelscited by 56
  12. 2024Diffusion Models and Representation Learning: A Surveycited by 53
38 more
  1. 2023Intriguing properties of generative classifierscited by 52
  2. 2023GSURE-Based Diffusion Model Training with Corrupted Datacited by 40
  3. 2023Stochastic Segmentation with Conditional Categorical Diffusion Modelscited by 38
  4. 2023SpectralDiff: A Generative Framework for Hyperspectral Image Classification with Diffusion Modelscited by 28
  5. 2024Your Diffusion Model is Secretly a Certifiably Robust Classifiercited by 24
  6. 2022Semantic uncertainty intervals for disentangled latent spacescited by 22
  7. 2023DifFSS: Diffusion Model for Few-Shot Semantic Segmentationcited by 22
  8. 2022Chroma-VAE: Mitigating Shortcut Learning with Generative Classifierscited by 17
  9. 2023Diffusion Models in Bioinformatics: A New Wave of Deep Learning Revolution in Actioncited by 15
  10. 2024IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Imagescited by 13
  11. 2022Increasing Confidence in Adversarial Robustness Evaluationscited by 12
  12. 2023Memory in Plain Sight: Surveying the Uncanny Resemblances of Associative Memories and Diffusion Modelscited by 12
  13. 2024InstructGIE: Towards Generalizable Image Editingcited by 11
  14. 2025Mitigating Hallucinations in Diffusion Models through Adaptive Attention Modulationcited by 11
  15. 2024A Simple and Efficient Baseline for Zero-Shot Generative Classificationcited by 7
  16. 2025Generative Classifiers Avoid Shortcut Solutionscited by 7
  17. 2023Bridge Diffusion Model: Bridge Chinese Text-to-Image Diffusion Model with English Communitiescited by 6
  18. 2025Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysiscited by 5
  19. 2024Solar synthetic imaging: Introducing denoising diffusion probabilistic models on SDO/AIA datacited by 4
  20. 2024CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defensecited by 4
  21. 2023Privacy Threats in Stable Diffusion Modelscited by 3
  22. 2024This Probably Looks Exactly Like That: An Invertible Prototypical Networkcited by 3
  23. 2024BGDB: Bernoulli-Gaussian Decision Block with Improved Denoising Diffusion Probabilistic Modelscited by 3
  24. 2025Language-Depth Navigated Thermal and Visible Image Fusioncited by 3
  25. 2025FS-Diff: Semantic guidance and clarity-aware simultaneous multimodal image fusion and super-resolutioncited by 3
  26. 2022Classification via score-based generative modellingcited by 2
  27. 2024Generative vs. Discriminative modeling under the lens of uncertainty quantificationcited by 2
  28. 2024From Graph Diffusion to Graph Classificationcited by 2
  29. 2024Pretrained Reversible Generation as Unsupervised Visual Representation Learningcited by 2
  30. 2025DIVE: Inverting Conditional Diffusion Models for Discriminative Taskscited by 2
  31. 2025Diffusion Models for Hyperspectral Image Analysis: A Comprehensive Reviewcited by 2
  32. 2025Your VAR Model is Secretly an Efficient and Explainable Generative Classifiercited by 2
  33. 2024CT-SDM: A Sampling Diffusion Model for Sparse-View CT Reconstruction across All Sampling Ratescited by 1
  34. 2024PGDiffSeg: Prior-Guided Denoising Diffusion Model with Parameter-Shared Attention for Breast Cancer Segmentationcited by 1
  35. 2024Supervised Score-Based Modeling by Gradient Boostingcited by 1
  36. 2025Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Reviewcited by 1
  37. 2025Advancing Image Classification with Discrete Diffusion Classification Modelingcited by 1
  38. 2023Training Image Derivatives: Increased Accuracy and Universal Robustnesscited by 0

50 most cited of 53 All 53 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2020Improved Techniques for Training Score-Based Generative Models
  2. 2023Assessing Robustness via Score-Based Adversarial Image Generation
  3. 2025Can Score-Based Generative Modeling Effectively Handle Medical Image Classification?
  4. 2023Score Mismatching for Generative Modeling
  5. 2024Moderating the Generalization of Score-based Generative Model
  6. 2024Score Neural Operator: A Generative Model for Learning and Generalizing Across Multiple Probability Distributions
  7. 2022Improved Analysis of Score-based Generative Modeling: User-Friendly Bounds under Minimal Smoothness Assumptions
  8. 2024A Good Score Does not Lead to A Good Generative Model