mlsanityData to 7 Oct 2026

Selective Classification for Deep Neural Networks

arXiv 1705.08500 ↗First posted 23 May 2017cs.LG cs.AIcited by 799

Not on the map. Why?

Cited by 59 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Selective classification techniques (also known as reject option) have not yet been considered in the context of deep neural networks (DNNs). These techniques can potentially significantly improve DNNs prediction performance by trading-off coverage. In this paper we propose a method to construct a selective classifier given a trained neural network. Our method allows a user to set a desired risk level. At test time, the classifier rejects instances as needed, to grant the desired risk (with high probability). Empirical results over CIFAR and ImageNet convincingly demonstrate the viability of our method, which opens up possibilities to operate DNNs in mission-critical applications. For example, using our method an unprecedented 2% error in top-5 ImageNet classification can be guaranteed with probability 99.9%, and almost 60% test coverage.

Key facts. Cited by 799 papers in the map (data through 7 Oct 2026). First posted on arXiv 23 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 38; 2022: 47; 2023: 68; 2024: 78; 2025: 87; 2026: 481.

799 papers.

Sort:

By area:

  1. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  2. 2022Solving math word problems with process- and outcome-based feedbackcited by 871
  3. 2023Just Ask for Calibration: Strategies for Eliciting Calibrated Confidence Scores from Language Models Fine-Tuned with Human Feedbackcited by 788
  4. 2022Improving alignment of dialogue agents via targeted human judgementscited by 527
  5. 2022Teaching language models to support answers with verified quotescited by 290
  6. 2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
  7. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  8. 2022Out-of-Distribution Detection and Selective Generation for Conditional Language Modelscited by 193
  9. 2022Leveraging Unlabeled Data to Predict Out-of-Distribution Performancecited by 141
  10. 2024Benchmark Data Contamination of Large Language Models: A Surveycited by 138
  11. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 132
  12. 2021Machine Learning with a Reject Option: A surveycited by 107
38 more
  1. 2024Trust or Escalate: LLM Judges with Provable Guarantees for Human Agreementcited by 99
  2. 2022Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectlycited by 86
  3. 2024Can Large Language Models Faithfully Express Their Intrinsic Uncertainty in Words?cited by 85
  4. 2024LUQ: Long-text Uncertainty Quantification for LLMscited by 79
  5. 2021Consistent Accelerated Inference via Confident Adaptive Transformerscited by 73
  6. 2022On the Relation between Sensitivity and Accuracy in In-context Learningcited by 71
  7. 2023Who Should Predict? Exact Algorithms For Learning to Defer to Humanscited by 68
  8. 2023Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Modelscited by 67
  9. 2022Investigating Selective Prediction Approaches Across Several Tasks in IID, OOD, and Adversarial Settingscited by 66
  10. 2022MaskTune: Mitigating Spurious Correlations by Forcing to Explorecited by 66
  11. 2021Optimal strategies for reject option classifierscited by 61
  12. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  13. 2022Confidence Score for Source-Free Unsupervised Domain Adaptationcited by 58
  14. 2024Mitigating LLM Hallucinations via Conformal Abstentioncited by 56
  15. 2025SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scalingcited by 54
  16. 2021DOCTOR: A Simple Method for Detecting Misclassification Errorscited by 52
  17. 2022A Call to Reflect on Evaluation Practices for Failure Detection in Image Classificationcited by 51
  18. 2024Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinationscited by 51
  19. 2022Predicting Out-of-Distribution Error with the Projection Normcited by 50
  20. 2024Conformal Alignment: Knowing When to Trust Foundation Models with Guaranteescited by 50
  21. 2023Adaptation with Self-Evaluation to Improve Selective Prediction in LLMscited by 49
  22. 2022Sample Efficient Learning of Predictors that Complement Humanscited by 46
  23. 2023Fusing Models with Complementary Expertisecited by 45
  24. 2023Rethinking Confidence Calibration for Failure Predictioncited by 43
  25. 2023OpenMix: Exploring Outlier Samples for Misclassification Detectioncited by 38
  26. 2023Llamas Know What GPTs Don't Show: Surrogate Models for Confidence Estimationcited by 38
  27. 2023Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithmscited by 36
  28. 2023What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifierscited by 35
  29. 2021Selective Regression Under Fairness Criteriacited by 34
  30. 2021Meta-Cal: Well-controlled Post-hoc Calibration by Rankingcited by 33
  31. 2021Role of Human-AI Interaction in Selective Predictioncited by 33
  32. 2022Domain Adaptation under Open Set Label Shiftcited by 32
  33. 2023Learning to Reject with a Fixed Predictor: Application to Decontextualizationcited by 32
  34. 2023A Survey on Out-of-Distribution Detection in NLPcited by 31
  35. 2024Consistency and Uncertainty: Identifying Unreliable Responses From Black-Box Vision-Language Models for Selective Visual Question Answeringcited by 31
  36. 2024Overcoming Common Flaws in the Evaluation of Selective Classification Systemscited by 31
  37. 2022Calibrated Selective Classificationcited by 30
  38. 2023Is Fine-tuning Needed? Pre-trained Language Models Are Near Perfect for Out-of-Domain Detectioncited by 29

50 most cited of 799 All 799 (JSON)