mlsanityData to 14 Oct 2026

Survey on Leveraging Uncertainty Estimation Towards Trustworthy Deep Neural Networks: The Case of Reject Option and Post-training Processing

arXiv 2304.04906 ↗First posted 11 Apr 2023cs.LG cs.CVcited by 7

Not on the map. Why?

Abstract (arXiv)

Although neural networks (especially deep neural networks) have achieved textitbetter-than-human performance in many fields, their real-world deployment is still questionable due to the lack of awareness about the limitation in their knowledge. To incorporate such awareness in the machine learning model, prediction with reject option (also known as selective classification or classification with abstention) has been proposed in literature. In this paper, we present a systematic review of the prediction with the reject option in the context of various neural networks. To the best of our knowledge, this is the first study focusing on this aspect of neural networks. Moreover, we discuss different novel loss functions related to the reject option and post-training processing (if any) of network output for generating suitable measurements for knowledge awareness of the model. Finally, we address the application of the rejection option in reducing the prediction time for the real-time problems and present a comprehensive summary of the techniques related to the reject option in the context of extensive variety of neural networks. Our code is available on GitHub: urlhttps://github.com/MehediHasanTutul/Rejectoption

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 47 of its 133 references that are in the map. First posted on arXiv 11 Apr 2023.

Builds on

47 of 133 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  4. 2017A Closer Look at Memorization in Deep Networkscited by 942
  5. 2017Selective Classification for Deep Neural Networkscited by 852
  6. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  8. 2015Towards Open Set Deep Networkscited by 538
  9. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  10. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 350
  11. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  12. 2018Additive Margin Softmax for Face Verificationcited by 278
35 more
  1. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 207
  2. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  3. 2019SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solvercited by 173
  4. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  5. 2018Bias-Reduced Uncertainty Estimation for Deep Neural Classifierscited by 113
  6. 2021Machine Learning with a Reject Option: A surveycited by 109
  7. 2022Reliable Visual Question Answering: Abstain Rather Than Answer Incorrectlycited by 89
  8. 2019Combating Label Noise in Deep Learning Using Abstentioncited by 86
  9. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  10. 2019Deep Gamblers: Learning to Abstain with Portfolio Theorycited by 71
  11. 2020Interpretability and Explainability: A Machine Learning Zoo Mini-tourcited by 55
  12. 2017IDK Cascades: Fast Deep Learning by Learning not to Overthinkcited by 48
  13. 2023What Can We Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifierscited by 35
  14. 2021GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularizationcited by 34
  15. 2022Calibrated Selective Classificationcited by 33
  16. 2020Regression with reject option and application to kNNcited by 30
  17. 2022Augmenting Softmax Information for Selective Classification with Out-of-Distribution Datacited by 27
  18. 2021An Effective Baseline for Robustness to Distributional Shiftcited by 25
  19. 2022Fine-grained TLS services classification with reject optioncited by 14
  20. 2018Deep-RBF Networks Revisited: Robust Classification with Rejectioncited by 10
  21. 2019Online Active Learning of Reject Option Classifierscited by 9
  22. 2021Controlled abstention neural networks for identifying skillful predictions for regression problemscited by 9
  23. 2019Selective prediction-set models with coverage guaranteescited by 6
  24. 2022ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy Statecited by 5
  25. 2019Leveraging Uncertainty in Deep Learning for Selective Classificationcited by 4
  26. 2020Dependency Decomposition and a Reject Option for Explainable Modelscited by 4
  27. 2021Controlled abstention neural networks for identifying skillful predictions for classification problemscited by 3
  28. 2021RISAN: Robust Instance Specific Abstention Networkcited by 2
  29. 2022A Deep Bayesian Neural Network for Cardiac Arrhythmia Classification with Rejection from ECG Recordingscited by 2
  30. 2019Generalized Learning with Rejection for Classification and Regression Problemscited by 1
  31. 2020Classification of Traffic Using Neural Networks by Rejecting: a Novel Approach in Classifying VPN Trafficcited by 1
  32. 2020Fine-grained Uncertainty Modeling in Neural Networkscited by 1
  33. 2020Understanding Local Robustness of Deep Neural Networks under Natural Variationscited by 1
  34. 2021Trading via Selective Classificationcited by 1
  35. 2022IDPS Signature Classification with a Reject Option and the Incorporation of Expert Knowledgecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 2; 2024: 1; 2025: 1; 2026: 3.

7 papers.

  1. 2024Calibrating Large Language Models Using Their Generations Onlycited by 65
  2. 2023How to Fix a Broken Confidence Estimator: Evaluating Post-hoc Methods for Selective Classification with Deep Neural Networkscited by 16
  3. 2025Estimating Semantic Alphabet Size for LLM Uncertainty Quantificationcited by 8
  4. 2026Adaptive Collaboration of Arena-Based Argumentative LLMs for Explainable and Contestable Legal Reasoningcited by 4
  5. 2023ChatGPT Prompting Cannot Estimate Predictive Uncertainty in High-Resource Languagescited by 2
  6. 2026DeferredSeg:A Multi-Expert Deferral Framework for Medical Image Segmentationcited by 1
  7. 2026Learning Adaptive Deliberation Control for Reliable Recognition with Multi-Agent Language Modelscited by 0