Data to 14 Oct 2026

Training Confidence-calibrated Classifiers for Detecting Out-of-Distribution Samples

arXiv 1711.09325 ↗First posted 26 Nov 2017stat.ML cs.LGcited by 389

Not on the map. Why?

Abstract (arXiv)

The problem of detecting whether a test sample is from in-distribution (i.e., training distribution by a classifier) or out-of-distribution sufficiently different from it arises in many real-world machine learning applications. However, the state-of-art deep neural networks are known to be highly overconfident in their predictions, i.e., do not distinguish in- and out-of-distributions. Recently, to handle this issue, several threshold-based detectors have been proposed given pre-trained neural classifiers. However, the performance of prior works highly depends on how to train the classifiers since they only focus on improving inference procedures. In this paper, we develop a novel training method for classifiers so that such inference algorithms can work better. In particular, we suggest two additional terms added to the original loss (e.g., cross entropy). The first one forces samples from out-of-distribution less confident by the classifier and the second one is for (implicitly) generating most effective training samples for the first one. In essence, our method jointly trains both classification and generative neural networks for out-of-distribution. We demonstrate its effectiveness using deep convolutional neural networks on various popular image datasets.

Key facts. Cited by 389 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 99; 2022: 77; 2023: 95; 2024: 70; 2025: 30; 2026: 18.

389 papers.

Sort:

By area:

2021Generalized Out-of-Distribution Detection: A Surveycited by 802
2021A Survey of Uncertainty in Deep Neural Networkscited by 680
2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
2023Towards Open Vocabulary Learning: A Surveycited by 166
2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154

38 more

2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 152
2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
2021Testing for Outliers with Conformal p-valuescited by 134
2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
2023Non-Parametric Outlier Synthesiscited by 129
2021Pixel-wise Anomaly Detection in Complex Driving Scenescited by 109
2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
2022Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectivescited by 98
2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
2022GMMSeg: Gaussian Mixture based Generative Semantic Segmentation Modelscited by 87
2022Training OOD Detectors in their Natural Habitatscited by 86
2023CompoDiff: Versatile Composed Image Retrieval With Latent Diffusioncited by 85
2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 71
2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 66
2023SoTTA: Robust Test-Time Adaptation on Noisy Data Streamscited by 63
2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 59
2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
2021Few-shot Conformal Prediction with Auxiliary Taskscited by 53
2021DOCTOR: A Simple Method for Detecting Misclassification Errorscited by 53
2021SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustnesscited by 49
2022A Simple Approach to Improve Single-Model Deep Uncertainty via Distance-Awarenesscited by 49
2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46
2021Posterior Meta-Replay for Continual Learningcited by 45
2023Uncertainty in Natural Language Processing: Sources, Quantification, and Applicationscited by 44
2022Self-Supervised Masking for Unsupervised Anomaly Detection and Localizationcited by 43
2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 43
2021Neural Mean Discrepancy for Efficient Out-of-Distribution Detectioncited by 42
2021Out-of-Scope Intent Detection with Self-Supervision and Discriminative Trainingcited by 42
2022DenseHybrid: Hybrid Anomaly Detection for Dense Open-set Recognitioncited by 42
2023On Advantages of Mask-level Recognition for Outlier-aware Segmentationcited by 42
2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38

50 most cited of 389 All 389 (JSON)