mlsanityData to 7 Oct 2026

Calibrated Out-of-Distribution Detection with a Generic Representation

arXiv 2303.13148 ↗First posted 23 Mar 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Out-of-distribution detection is a common issue in deploying vision models in practice and solving it is an essential building block in safety critical applications. Most of the existing OOD detection solutions focus on improving the OOD robustness of a classification model trained exclusively on in-distribution (ID) data. In this work, we take a different approach and propose to leverage generic pre-trained representation. We propose a novel OOD method, called GROOD, that formulates the OOD detection as a Neyman-Pearson task with well calibrated scores and which achieves excellent performance, predicated by the use of a good generic representation. Only a trivial training process is required for adapting GROOD to a particular problem. The method is simple, general, efficient, calibrated and with only a few hyper-parameters. The method achieves state-of-the-art performance on a number of OOD benchmarks, reaching near perfect performance on several of them. The source code is available at https://github.com/vojirt/GROOD.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 38 of its 56 references that are in the map. First posted on arXiv 23 Mar 2023.

Builds on

38 of 56 references.

References · 38

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  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. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  9. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  11. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  12. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
26 more
  1. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  2. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  5. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  6. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  7. 2020Generalized ODIN: Detecting Out-of-distribution Image without Learning from Out-of-distribution Datacited by 408
  8. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  9. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  10. 2019On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networkscited by 304
  11. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  12. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  13. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  14. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  15. 2018Reducing Network Agnostophobiacited by 165
  16. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  17. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
  18. 2021SegmentMeIfYouCan: A Benchmark for Anomaly Segmentationcited by 150
  19. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  20. 2020Hybrid Models for Open Set Recognitioncited by 109
  21. 2021Semantically Coherent Out-of-Distribution Detectioncited by 107
  22. 2023Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Trainingcited by 91
  23. 2022Anomaly Detection in Autonomous Driving: A Surveycited by 87
  24. 2022Continual Learning with Foundation Models: An Empirical Study of Latent Replaycited by 61
  25. 2021A Survey on Open Set Recognitioncited by 25
  26. 2022Breaking Down Out-of-Distribution Detection: Many Methods Based on OOD Training Data Estimate a Combination of the Same Core Quantitiescited by 23

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 4.

8 papers.

  1. 2024Outlier detection by ensembling uncertainty with negative objectnesscited by 34
  2. 2024PixOOD: Pixel-Level Out-of-Distribution Detectioncited by 20
  3. 2025Out-of-Distribution Segmentation in Autonomous Driving: Problems and State of the Artcited by 13
  4. 2024A Likelihood Ratio-Based Approach to Segmenting Unknown Objectscited by 12
  5. 2025Improving Wildlife Out-of-Distribution Detection: Africas Big Fivecited by 2
  6. 2023A Comprehensive Assessment Benchmark for Rigorously Evaluating Deep Learning Image Classifierscited by 1
  7. 2025From Pixel to Mask: A Survey of Out-of-Distribution Segmentationcited by 1
  8. 2025Nearest-Class Mean and Logits Agreement for Wildlife Open-Set Recognitioncited by 1