mlsanityData to 14 Oct 2026

Energy-based Hopfield Boosting for Out-of-Distribution Detection

arXiv 2405.08766 ↗First posted 14 May 2024cs.LG cs.CVcited by 9

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution (OOD) detection is critical when deploying machine learning models in the real world. Outlier exposure methods, which incorporate auxiliary outlier data in the training process, can drastically improve OOD detection performance compared to approaches without advanced training strategies. We introduce Hopfield Boosting, a boosting approach, which leverages modern Hopfield energy (MHE) to sharpen the decision boundary between the in-distribution and OOD data. Hopfield Boosting encourages the model to concentrate on hard-to-distinguish auxiliary outlier examples that lie close to the decision boundary between in-distribution and auxiliary outlier data. Our method achieves a new state-of-the-art in OOD detection with outlier exposure, improving the FPR95 metric from 2.28 to 0.92 on CIFAR-10 and from 11.76 to 7.94 on CIFAR-100.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 57 of its 95 references that are in the map. First posted on arXiv 14 May 2024.

Builds on

57 of 95 references.

References · 57

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  7. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  8. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  9. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  11. 2013Describing Textures in the Wildcited by 2,125
  12. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
38 more
  1. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  4. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  5. 2021Towards Total Recall in Industrial Anomaly Detectioncited by 776
  6. 2021ImageNet-21K Pretraining for the Massescited by 613
  7. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
  8. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  9. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  10. 2020Hopfield Networks is All You Needcited by 475
  11. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  12. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  13. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  14. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  15. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  16. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  17. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  18. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 268
  19. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  20. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
  21. 2016Dense Associative Memory for Pattern Recognitioncited by 236
  22. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  23. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  24. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  25. 2023Non-Parametric Outlier Synthesiscited by 129
  26. 2020ATOM: Robustifying Out-of-distribution Detection Using Outlier Miningcited by 116
  27. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  28. 2017Global Convergence of Langevin Dynamics Based Algorithms for Nonconvex Optimizationcited by 97
  29. 2021CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIPcited by 89
  30. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  31. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
  32. 2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 66
  33. 2014Consistency and fluctuations for stochastic gradient Langevin dynamicscited by 65
  34. 2020Modern Hopfield Networks and Attention for Immune Repertoire Classificationcited by 53
  35. 2019Semantic-Aware Scene Recognitioncited by 43
  36. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 43
  37. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
  38. 2023Conformal Prediction for Time Series with Modern Hopfield Networkscited by 42

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 2.

9 papers.

  1. 2024Provably Optimal Memory Capacity for Modern Hopfield Models: Transformer-Compatible Dense Associative Memories as Spherical Codescited by 19
  2. 2024SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximationcited by 10
  3. 2025Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoringcited by 3
  4. 2025Automatic Grid Updates for Kolmogorov-Arnold Networks using Layer Histogramscited by 3
  5. 2025Activation Subspaces for Out-of-Distribution Detectioncited by 2
  6. 2025On the Role of Hidden States of Modern Hopfield Network in Transformercited by 1
  7. 2026AP-OOD: Attention Pooling for Out-of-Distribution Detectioncited by 1
  8. 2025Out-of-Distribution Detection in Heterogeneous Graphs via Energy Propagationcited by 0
  9. 2026Continual Learning in Modern Hopfield Networks with an Application to Diffusion Modelscited by 0