mlsanityData to 7 Oct 2026

Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

arXiv 1912.03263 ↗First posted 6 Dec 2019cs.LG cs.CV stat.MLcited by 402

Not on the map. Why?

Cited by 53 in Diffusion models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x,y). In this setting, the standard class probabilities can be easily computed as well as unnormalized values of p(x) and p(x|y). Within this framework, standard discriminative architectures may beused and the model can also be trained on unlabeled data. We demonstrate that energy based training of the joint distribution improves calibration, robustness, andout-of-distribution detection while also enabling our models to generate samplesrivaling the quality of recent GAN approaches. We improve upon recently proposed techniques for scaling up the training of energy based models and presentan approach which adds little overhead compared to standard classification training. Our approach is the first to achieve performance rivaling the state-of-the-artin both generative and discriminative learning within one hybrid model.

Key facts. Cited by 402 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 77; 2022: 71; 2023: 87; 2024: 62; 2025: 54; 2026: 50.

402 papers.

Sort:

By area:

  1. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  3. 2022Diffusion Models for Adversarial Purificationcited by 469
  4. 2021Implicit Behavioral Cloningcited by 442
  5. 2021Explaining Neural Scaling Lawscited by 353
  6. 2023Iterative Preference Learning from Human Feedback: Bridging Theory and Practice for RLHF under KL-Constraintcited by 346
  7. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  8. 2023Your Diffusion Model is Secretly a Zero-Shot Classifiercited by 301
  9. 2021How to Train Your Energy-Based Modelscited by 271
  10. 2022The Forward-Forward Algorithm: Some Preliminary Investigationscited by 262
  11. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  12. 2023Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcited by 216
38 more
  1. 2022Convergence of score-based generative modeling for general data distributionscited by 179
  2. 2022Convergence for score-based generative modeling with polynomial complexitycited by 176
  3. 2021Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalizationcited by 141
  4. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  5. 2021Adversarial purification with Score-based generative modelscited by 132
  6. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 109
  7. 2021Energy-Based Learning for Scene Graph Generationcited by 104
  8. 2022Let us Build Bridges: Understanding and Extending Diffusion Generative Modelscited by 102
  9. 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
  10. 2022Exploring Chemical Space with Score-based Out-of-distribution Generationcited by 95
  11. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  12. 2021Oops I Took A Gradient: Scalable Sampling for Discrete Distributionscited by 92
  13. 2021Domain Impression: A Source Data Free Domain Adaptation Methodcited by 91
  14. 2022Guided Diffusion Model for Adversarial Purificationcited by 90
  15. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  16. 2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
  17. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  18. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 79
  19. 2023Robust Classification via a Single Diffusion Modelcited by 79
  20. 2021Learning to Compose Visual Relationscited by 72
  21. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  22. 2021Unsupervised Learning of Compositional Energy Conceptscited by 71
  23. 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67
  24. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 67
  25. 2024Variational Bayesian Last Layerscited by 67
  26. 2022Mix and Match: Learning-free Controllable Text Generation using Energy Language Modelscited by 66
  27. 2021Controllable and Compositional Generation with Latent-Space Energy-Based Modelscited by 64
  28. 2022Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Modelcited by 58
  29. 2022PROB: Probabilistic Objectness for Open World Object Detectioncited by 57
  30. 2021Scalable Bayesian Inverse Reinforcement Learningcited by 56
  31. 2020Strictly Batch Imitation Learning by Energy-based Distribution Matchingcited by 54
  32. 2021Score-Based Generative Classifierscited by 53
  33. 2021Active Learning for Domain Adaptation: An Energy-Based Approachcited by 53
  34. 2022Boosting Out-of-distribution Detection with Typical Featurescited by 48
  35. 2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46
  36. 2022A Tale of Two Flows: Cooperative Learning of Langevin Flow and Normalizing Flow Toward Energy-Based Modelcited by 44
  37. 2022Isolation and Impartial Aggregation: A Paradigm of Incremental Learning without Interferencecited by 44
  38. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43

50 most cited of 402 All 402 (JSON)