mlsanityData to 14 Oct 2026

Back to the Basics: Revisiting Out-of-Distribution Detection Baselines

arXiv 2207.03061 ↗First posted 7 Jul 2022cs.LG cs.CV stat.MLcited by 16

Not on the map. Why?

Abstract (arXiv)

We study simple methods for out-of-distribution (OOD) image detection that are compatible with any already trained classifier, relying on only its predictions or learned representations. Evaluating the OOD detection performance of various methods when utilized with ResNet-50 and Swin Transformer models, we find methods that solely consider the model's predictions can be easily outperformed by also considering the learned representations. Based on our analysis, we advocate for a dead-simple approach that has been neglected in other studies: simply flag as OOD images whose average distance to their K nearest neighbors is large (in the representation space of an image classifier trained on the in-distribution data).

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Builds on 21 of its 29 references that are in the map. First posted on arXiv 7 Jul 2022.

Builds on

21 of 29 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  5. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  7. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  8. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  9. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 453
  10. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  11. 2020AutoGluon-Tabular: Robust and Accurate AutoML for Structured Datacited by 383
  12. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
9 more
  1. 2020Are we done with ImageNet?cited by 333
  2. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  3. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 207
  4. 2018ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithmscited by 130
  5. 2020Deep Nearest Neighbor Anomaly Detectioncited by 104
  6. 2021Understanding Failures in Out-of-Distribution Detection with Deep Generative Modelscited by 89
  7. 2020Robust Out-of-distribution Detection for Neural Networkscited by 57
  8. 2019Maximizing Overall Diversity for Improved Uncertainty Estimates in Deep Ensemblescited by 30
  9. 2020Analysis of KNN Density Estimationcited by 28

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 5; 2025: 2; 2026: 1.

16 papers.

Sort:

By area:

  1. 2023Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothnesscited by 15
  2. 2023How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?cited by 14
  3. 2023Continual Evidential Deep Learning for Out-of-Distribution Detectioncited by 11
  4. 2024FodFoM: Fake Outlier Data by Foundation Models Creates Stronger Visual Out-of-Distribution Detectorcited by 10
  5. 2023Manifold DivideMix: A Semi-Supervised Contrastive Learning Framework for Severe Label Noisecited by 9
  6. 2024Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoningcited by 8
  7. 2024TagFog: Textual Anchor Guidance and Fake Outlier Generation for Visual Out-of-Distribution Detectioncited by 8
  8. 2023Classical Out-of-Distribution Detection Methods Benchmark in Text Classification Taskscited by 5
  9. 2024WeiPer: OOD Detection using Weight Perturbations of Class Projectionscited by 4
  10. 2023Nearest Neighbor Based Out-of-Distribution Detection in Remote Sensing Scene Classificationcited by 1
  11. 2026DeMix: Debugging Training Data with Mixed Data Error Types by Investigating Influence Vectorscited by 1
  12. 2023Detecting Errors in a Numerical Response via any Regression Modelcited by 0
4 more
  1. 2023Image Outlier Detection Without Training using RANSACcited by 0
  2. 2024Probabilistic Contrastive Learning with Explicit Concentration on the Hyperspherecited by 0
  3. 2025ConceptVAE: Self-Supervised Fine-Grained Concept Disentanglement from 2D Echocardiographiescited by 0
  4. 2025A Data-Centric Perspective on the Influence of Image Data Quality in Machine Learning Modelscited by 0