mlsanityData to 7 Oct 2026

OpenMix: Exploring Outlier Samples for Misclassification Detection

arXiv 2303.17093 ↗First posted 30 Mar 2023cs.LG cs.AIcited by 38

Not on the map. Why?

Abstract (arXiv)

Reliable confidence estimation for deep neural classifiers is a challenging yet fundamental requirement in high-stakes applications. Unfortunately, modern deep neural networks are often overconfident for their erroneous predictions. In this work, we exploit the easily available outlier samples, i.e., unlabeled samples coming from non-target classes, for helping detect misclassification errors. Particularly, we find that the well-known Outlier Exposure, which is powerful in detecting out-of-distribution (OOD) samples from unknown classes, does not provide any gain in identifying misclassification errors. Based on these observations, we propose a novel method called OpenMix, which incorporates open-world knowledge by learning to reject uncertain pseudo-samples generated via outlier transformation. OpenMix significantly improves confidence reliability under various scenarios, establishing a strong and unified framework for detecting both misclassified samples from known classes and OOD samples from unknown classes. The code is publicly available at https://github.com/Impression2805/OpenMix.

Key facts. Cited by 38 papers in the map (data through 7 Oct 2026). Builds on 52 of its 70 references that are in the map. First posted on arXiv 30 Mar 2023.

Builds on

52 of 70 references.

References · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2016Densely Connected Convolutional Networkscited by 6,691
  4. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  7. 2016Wide Residual Networkscited by 3,057
  8. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  9. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  10. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  11. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  12. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
38 more
  1. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  4. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  5. 2019When Does Label Smoothing Help?cited by 985
  6. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  7. 2017Selective Classification for Deep Neural Networkscited by 799
  8. 2020Long-tail learning via logit adjustmentcited by 605
  9. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  10. 2020Calibrating Deep Neural Networks using Focal Losscited by 353
  11. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  12. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  13. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  14. 2018To Trust Or Not To Trust A Classifiercited by 205
  15. 2019Addressing Failure Prediction by Learning Model Confidencecited by 183
  16. 2017Computer Vision for Autonomous Vehicles: Problems, Datasets and State of the Artcited by 182
  17. 2020Confidence-Aware Learning for Deep Neural Networkscited by 113
  18. 2020Revisiting Training Strategies and Generalization Performance in Deep Metric Learningcited by 99
  19. 2021Label-Imbalanced and Group-Sensitive Classification under Overparameterizationcited by 74
  20. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
  21. 2021DOCTOR: A Simple Method for Detecting Misclassification Errorscited by 52
  22. 2021Trustworthy Long-Tailed Classificationcited by 51
  23. 2022A Call to Reflect on Evaluation Practices for Failure Detection in Image Classificationcited by 51
  24. 2022Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognitioncited by 44
  25. 2023Rethinking Confidence Calibration for Failure Predictioncited by 43
  26. 2021Neural Mean Discrepancy for Efficient Out-of-Distribution Detectioncited by 42
  27. 2022Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Imagescited by 35
  28. 2020Confidence Estimation via Auxiliary Modelscited by 33
  29. 2020Towards Robust Pattern Recognition: A Reviewcited by 31
  30. 2022The Familiarity Hypothesis: Explaining the Behavior of Deep Open Set Methodscited by 28
  31. 2022RegMixup: Mixup as a Regularizer Can Surprisingly Improve Accuracy and Out Distribution Robustnesscited by 27
  32. 2022Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasetscited by 25
  33. 2021Removing Undesirable Feature Contributions Using Out-of-Distribution Datacited by 23
  34. 2022Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantitiescited by 23
  35. 2021A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networkscited by 19
  36. 2023The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognitioncited by 16
  37. 2022POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samplescited by 15
  38. 2023Average of Pruning: Improving Performance and Stability of Out-of-Distribution Detectioncited by 14

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 18; 2025: 10; 2026: 6.

38 papers.

Sort:

By area:

  1. 2024Overcoming Common Flaws in the Evaluation of Selective Classification Systemscited by 31
  2. 2023Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learningcited by 23
  3. 2023A Data-Driven Measure of Relative Uncertainty for Misclassification Detectioncited by 14
  4. 2024Local-Prompt: Extensible Local Prompts for Few-Shot Out-of-Distribution Detectioncited by 14
  5. 2025Handling Out-of-Distribution Data: A Surveycited by 14
  6. 2024Gradient-Regularized Out-of-Distribution Detectioncited by 13
  7. 2024Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifierscited by 10
  8. 2023Unified Classification and Rejection: A One-versus-All Frameworkcited by 9
  9. 2024Revisiting Confidence Estimation: Towards Reliable Failure Predictioncited by 9
  10. 2024Energy-based Hopfield Boosting for Out-of-Distribution Detectioncited by 9
  11. 2024SURE: SUrvey REcipes for building reliable and robust deep networkscited by 8
  12. 2025Interpretable Failure Detection with Human-Level Conceptscited by 7
26 more
  1. 2024Typicalness-Aware Learning for Failure Detectioncited by 6
  2. 2024Out-Of-Distribution Detection with Diversification (Provably)cited by 6
  3. 2025Generalized Category Discovery via Reciprocal Learning and Class-Wise Distribution Regularizationcited by 6
  4. 2024Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forwardcited by 5
  5. 2024Zero-Shot Out-of-Distribution Detection with Outlier Label Exposurecited by 5
  6. 2024Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processescited by 4
  7. 2024Margin-bounded Confidence Scores for Out-of-Distribution Detectioncited by 4
  8. 2024Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptationcited by 4
  9. 2025To Trust Or Not To Trust Your Vision-Language Model's Predictioncited by 3
  10. 2024All Beings Are Equal in Open Set Recognitioncited by 2
  11. 2024Evaluation and Improvement of Fault Detection for Large Language Modelscited by 1
  12. 2025Probing Network Decisions: Capturing Uncertainties and Unveiling Vulnerabilities Without Label Informationcited by 1
  13. 2025Towards Efficient and General-Purpose Few-Shot Misclassification Detection for Vision-Language Modelscited by 1
  14. 2025Enhancing Multi-view Open-set Learning via Ambiguity Uncertainty Calibration and View-wise Debiasingcited by 1
  15. 2026Adaptive Confidence Regularization for Multimodal Failure Detectioncited by 1
  16. 2023Be Bayesian by Attachments to Catch More Uncertaintycited by 0
  17. 2024RICASSO: Reinforced Imbalance Learning with Class-Aware Self-Supervised Outliers Exposurecited by 0
  18. 2024Mining In-distribution Attributes in Outliers for Out-of-distribution Detectioncited by 0
  19. 2025RAT: Boosting Misclassification Detection Ability without Extra Datacited by 0
  20. 2025TrustLoRA: Low-Rank Adaptation for Failure Detection under Out-of-distribution Datacited by 0
  21. 2025TRUST: Test-time Resource Utilization for Superior Trustworthinesscited by 0
  22. 2026Cognitive Fusion of ZC Sequences and Time-Frequency Images for Out-of-Distribution Detection of Drone Signalscited by 0
  23. 2026Diffusion-Inspired Reconfiguration of Transformers for Uncertainty Calibrationcited by 0
  24. 2026X-MAP: eXplainable Misclassification Analysis and Profiling for Spam and Phishing Detectioncited by 0
  25. 2026From Misclassifications to Outliers: Joint Reliability Assessment in Classificationcited by 0
  26. 2026ECUASn: A family of metrics for principled evaluation of uncertainty-augmented systemscited by 0