mlsanityData to 7 Oct 2026

The Extreme Value Machine

arXiv 1506.06112 ↗First posted 19 Jun 2015cs.LGcited by 78

Not on the map. Why?

Abstract (arXiv)

It is often desirable to be able to recognize when inputs to a recognition function learned in a supervised manner correspond to classes unseen at training time. With this ability, new class labels could be assigned to these inputs by a human operator, allowing them to be incorporated into the recognition function --- ideally under an efficient incremental update mechanism. While good algorithms that assume inputs from a fixed set of classes exist, e.g., artificial neural networks and kernel machines, it is not immediately obvious how to extend them to perform incremental learning in the presence of unknown query classes. Existing algorithms take little to no distributional information into account when learning recognition functions and lack a strong theoretical foundation. We address this gap by formulating a novel, theoretically sound classifier --- the Extreme Value Machine (EVM). The EVM has a well-grounded interpretation derived from statistical Extreme Value Theory (EVT), and is the first classifier to be able to perform nonlinear kernel-free variable bandwidth incremental learning. Compared to other classifiers in the same deep network derived feature space, the EVM is accurate and efficient on an established benchmark partition of the ImageNet dataset.

Key facts. Cited by 78 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jun 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 26; 2022: 11; 2023: 21; 2024: 5; 2025: 10; 2026: 5.

78 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2021Open-World Semi-Supervised Learningcited by 165
  3. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  4. 2022FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learningcited by 120
  5. 2021Towards Discovery and Attribution of Open-world GAN Generated Imagescited by 66
  6. 2021Learning Bounds for Open-Set Learningcited by 27
  7. 2023Open Set Action Recognition via Multi-Label Evidential Learningcited by 26
  8. 2021A Survey on Open Set Recognitioncited by 25
  9. 2023CNS-Net: Conservative Novelty Synthesizing Network for Malware Recognition in an Open-set Scenariocited by 15
  10. 2025vCache: Verified Semantic Prompt Cachingcited by 15
  11. 2021Deep Learning and Traffic Classification: Lessons learned from a commercial-grade dataset with hundreds of encrypted and zero-day applicationscited by 14
  12. 2024Open World Object Detection: A Surveycited by 13
38 more
  1. 2021Towards Visual Semanticscited by 12
  2. 2022Regression modelling of spatiotemporal extreme U.S. wildfires via partially-interpretable neural networkscited by 11
  3. 2021Collective Decision of One-vs-Rest Networks for Open Set Recognitioncited by 10
  4. 2022Towards Accurate Open-Set Recognition via Background-Class Regularizationcited by 10
  5. 2023Glocal Energy-based Learning for Few-Shot Open-Set Recognitioncited by 10
  6. 2023MDENet: Multi-modal Dual-embedding Networks for Malware Open-set Recognitioncited by 10
  7. 2023A VAE Approach to Sample Multivariate Extremescited by 9
  8. 2021Self-Supervised Features Improve Open-World Learningcited by 8
  9. 2021Bayesian Embeddings for Few-Shot Open World Recognitioncited by 8
  10. 2022Measuring Human Perception to Improve Open Set Recognitioncited by 7
  11. 2022Large-Scale Open-Set Classification Protocols for ImageNetcited by 7
  12. 2024AI, Meet Human: Learning Paradigms for Hybrid Decision Making Systemscited by 7
  13. 2023WOT-Class: Weakly Supervised Open-world Text Classificationcited by 6
  14. 2021Deep Compact Polyhedral Conic Classifier for Open and Closed Set Recognitioncited by 5
  15. 2021Evaluation of Various Open-Set Medical Imaging Tasks with Deep Neural Networkscited by 5
  16. 2021Human-in-the-loop Handling of Knowledge Driftcited by 4
  17. 2023Managing the unknown: a survey on Open Set Recognition and tangential areascited by 4
  18. 2021EMG Signal Classification Using Reflection Coefficients and Extreme Value Machinecited by 3
  19. 2021Incremental Deep Neural Network Learning using Classification Confidence Thresholdingcited by 3
  20. 2022PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learningcited by 3
  21. 2023Vocabulary-informed Zero-shot and Open-set Learningcited by 3
  22. 2023Egocentric Hierarchical Visual Semanticscited by 3
  23. 2023OpenGCD: Assisting Open World Recognition with Generalized Category Discoverycited by 3
  24. 2023Open-set Face Recognition using Ensembles trained on Clustered Datacited by 3
  25. 2021Unsupervised detection and open-set classification of fast-ramped flexibility activation eventscited by 2
  26. 2022Reconstructing Humpty Dumpty: Multi-feature Graph Autoencoder for Open Set Action Recognitioncited by 2
  27. 2022Human Activity Recognition in an Open Worldcited by 2
  28. 2023M-Tuning: Prompt Tuning with Mitigated Label Bias in Open-Set Scenarioscited by 2
  29. 2023torchosr -- a PyTorch extension package for Open Set Recognition models evaluation in Pythoncited by 2
  30. 2023A Generalized Unbiased Risk Estimator for Learning with Augmented Classescited by 2
  31. 2023LORD: Leveraging Open-Set Recognition with Unknown Datacited by 2
  32. 2024Near OOD Detection for Vision-Language Prompt Learning with Contrastive Logit Scorecited by 2
  33. 2024Large-Scale Evaluation of Open-Set Image Classification Techniquescited by 2
  34. 2024Zero-shot Hazard Identification in Autonomous Driving: A Case Study on the COOOL Benchmarkcited by 2
  35. 2025Improving Wildlife Out-of-Distribution Detection: Africas Big Fivecited by 2
  36. 2025UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasetscited by 2
  37. 2021Incrementally Zero-Shot Detection by an Extreme Value Analyzercited by 1
  38. 2021Handwriting Recognition with Noveltycited by 1

50 most cited of 78 All 78 (JSON)