mlsanityData to 7 Oct 2026

On the Impact of Spurious Correlation for Out-of-distribution Detection

arXiv 2109.05642 ↗First posted 12 Sep 2021cs.LG cs.AIcited by 68

Not on the map. Why?

Abstract (arXiv)

Modern neural networks can assign high confidence to inputs drawn from outside the training distribution, posing threats to models in real-world deployments. While much research attention has been placed on designing new out-of-distribution (OOD) detection methods, the precise definition of OOD is often left in vagueness and falls short of the desired notion of OOD in reality. In this paper, we present a new formalization and model the data shifts by taking into account both the invariant and environmental (spurious) features. Under such formalization, we systematically investigate how spurious correlation in the training set impacts OOD detection. Our results suggest that the detection performance is severely worsened when the correlation between spurious features and labels is increased in the training set. We further show insights on detection methods that are more effective in reducing the impact of spurious correlation and provide theoretical analysis on why reliance on environmental features leads to high OOD detection error. Our work aims to facilitate a better understanding of OOD samples and their formalization, as well as the exploration of methods that enhance OOD detection.

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). Builds on 39 of its 52 references that are in the map. First posted on arXiv 12 Sep 2021.

Builds on

39 of 52 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  6. 2013Describing Textures in the Wildcited by 2,110
  7. 2019Invariant Risk Minimizationcited by 1,832
  8. 2018Glow: Generative Flow with Invertible 1x1 Convolutionscited by 1,539
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  10. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  11. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  12. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
27 more
  1. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  2. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  3. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,232
  4. 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
  5. 2020In Search of Lost Domain Generalizationcited by 1,042
  6. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  7. 2020Out-of-Distribution Generalization via Risk Extrapolation (REx)cited by 737
  8. 2018Recognition in Terra Incognitacited by 655
  9. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 533
  10. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  11. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  12. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  13. 2018Confounding variables can degrade generalization performance of radiological deep learning modelscited by 374
  14. 2020Noise or Signal: The Role of Image Backgrounds in Object Recognitioncited by 342
  15. 2020The Risks of Invariant Risk Minimizationcited by 262
  16. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  17. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  18. 2019Learning De-biased Representations with Biased Representationscited by 199
  19. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  20. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  21. 2015TurkerGaze: Crowdsourcing Saliency with Webcam based Eye Trackingcited by 165
  22. 2020Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encodercited by 145
  23. 2020Heterogeneous Domain Generalization via Domain Mixupcited by 103
  24. 2021MOOD: Multi-level Out-of-distribution Detectioncited by 94
  25. 2021Does Your Dermatology Classifier Know What It Doesn't Know? Detecting the Long-Tail of Unseen Conditionscited by 68
  26. 2016Object Recognition with and without Objectscited by 39
  27. 2019Detecting Out-of-Distribution Examples with In-distribution Examples and Gram Matricescited by 32

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 10; 2023: 22; 2024: 20; 2025: 8; 2026: 5.

68 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  3. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  4. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  5. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  6. 2022POEM: Out-of-Distribution Detection with Posterior Samplingcited by 108
  7. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  8. 2024ARGS: Alignment as Reward-Guided Searchcited by 99
  9. 2021Provable Guarantees for Understanding Out-of-distribution Detectioncited by 78
  10. 2024Process Reward Model with Q-Value Rankingscited by 78
  11. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Modelscited by 66
  12. 2022Full-Spectrum Out-of-Distribution Detectioncited by 63
38 more
  1. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  2. 2022Are Vision Transformers Robust to Spurious Correlations?cited by 36
  3. 2024How Does Unlabeled Data Provably Help Out-of-Distribution Detection?cited by 36
  4. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  5. 2024MM-SpuBench: Towards Better Understanding of Spurious Biases in Multimodal LLMscited by 33
  6. 2023Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sourcescited by 31
  7. 2023Understanding the Feature Norm for Out-of-Distribution Detectioncited by 25
  8. 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 15
  9. 2023ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentationcited by 14
  10. 2023Unified Out-Of-Distribution Detection: A Model-Specific Perspectivecited by 13
  11. 2022The Value of Out-of-Distribution Datacited by 12
  12. 2023Domain Generalization via Nuclear Norm Regularizationcited by 12
  13. 2023Exploring Large Language Models for Multi-Modal Out-of-Distribution Detectioncited by 12
  14. 2023On the Powerfulness of Textual Outlier Exposure for Visual OoD Detectioncited by 12
  15. 2022Towards out of distribution generalization for problems in mechanicscited by 11
  16. 2023Meta OOD Learning for Continuously Adaptive OOD Detectioncited by 10
  17. 2023Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Modelscited by 9
  18. 2023Invariant Anomaly Detection under Distribution Shifts: A Causal Perspectivecited by 8
  19. 2024On the Learnability of Out-of-distribution Detectioncited by 8
  20. 2023Using Semantic Information for Defining and Detecting OOD Inputscited by 6
  21. 2024When and How Does In-Distribution Label Help Out-of-Distribution Detection?cited by 6
  22. 2024Insect Identification in the Wild: The AMI Datasetcited by 6
  23. 2024Rethinking Out-of-Distribution Detection on Imbalanced Data Distributioncited by 6
  24. 2023Likelihood-Aware Semantic Alignment for Full-Spectrum Out-of-Distribution Detectioncited by 5
  25. 2024Towards Adversarial Robustness via Debiased High-Confidence Logit Alignmentcited by 5
  26. 2024Focus On This, Not That! Steering LLMs with Adaptive Feature Specificationcited by 5
  27. 2025TailedCore: Few-Shot Sampling for Unsupervised Long-Tail Noisy Anomaly Detectioncited by 5
  28. 2023Robustness to Spurious Correlations Improves Semantic Out-of-Distribution Detectioncited by 4
  29. 2024Say My Name: a Model's Bias Discovery Frameworkcited by 4
  30. 2024What If the Input is Expanded in OOD Detection?cited by 4
  31. 2022Key Feature Replacement of In-Distribution Samples for Out-of-Distribution Detectioncited by 3
  32. 2023Studying Generalization on Memory-Based Methods in Continual Learningcited by 3
  33. 2023Towards Effective Semantic OOD Detection in Unseen Domains: A Domain Generalization Perspectivecited by 3
  34. 2025BackMix: Regularizing Open Set Recognition by Removing Underlying Fore-Background Priorscited by 3
  35. 2023Pushing the Accuracy-Group Robustness Frontier with Introspective Self-playcited by 2
  36. 2025Spurious-Aware Prototype Refinement for Reliable Out-of-Distribution Detectioncited by 2
  37. 2025NegRefine: Refining Negative Label-Based Zero-Shot OOD Detectioncited by 2
  38. 2023Contrastive variational information bottleneck for aspect-based sentiment analysiscited by 1

50 most cited of 68 All 68 (JSON)