mlsanityData to 7 Oct 2026

Detecting OODs as datapoints with High Uncertainty

arXiv 2108.06380 ↗First posted 13 Aug 2021cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) are known to produce incorrect predictions with very high confidence on out-of-distribution inputs (OODs). This limitation is one of the key challenges in the adoption of DNNs in high-assurance systems such as autonomous driving, air traffic management, and medical diagnosis. This challenge has received significant attention recently, and several techniques have been developed to detect inputs where the model's prediction cannot be trusted. These techniques detect OODs as datapoints with either high epistemic uncertainty or high aleatoric uncertainty. We demonstrate the difference in the detection ability of these techniques and propose an ensemble approach for detection of OODs as datapoints with high uncertainty (epistemic or aleatoric). We perform experiments on vision datasets with multiple DNN architectures, achieving state-of-the-art results in most cases.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 18 of its 37 references that are in the map. First posted on arXiv 13 Aug 2021.

Builds on

18 of 37 references.

References · 18

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  7. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  9. 2016End to End Learning for Self-Driving Carscited by 1,000
  10. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  11. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  12. 2018Deep Learning for Classical Japanese Literaturecited by 415
6 more
  1. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  2. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  3. 2020Classification-Based Anomaly Detection for General Datacited by 210
  4. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
  5. 2015Contextual Action Recognition with R*CNNcited by 33
  6. 2016Unsupervised Risk Estimation Using Only Conditional Independence Structurecited by 17

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 1; 2024: 1; 2025: 1.

7 papers.

  1. 2022iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detectioncited by 27
  2. 2024Data Augmentation for Image Classification using Generative AIcited by 11
  3. 2023Using Semantic Information for Defining and Detecting OOD Inputscited by 6
  4. 2021Unity is strength: Improving the Detection of Adversarial Examples with Ensemble Approachescited by 3
  5. 2025Safety Monitoring for Learning-Enabled Cyber-Physical Systems in Out-of-Distribution Scenarioscited by 3
  6. 2021FROB: Few-shot ROBust Model for Classification and Out-of-Distribution Detectioncited by 2
  7. 2022CODiT: Conformal Out-of-Distribution Detection in Time-Series Datacited by 2