mlsanityData to 7 Oct 2026

CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning

arXiv 2210.01742 ↗First posted 4 Oct 2022cs.LG cs.CVcited by 11

Not on the map. Why?

Abstract (arXiv)

Handling out-of-distribution (OOD) samples has become a major stake in the real-world deployment of machine learning systems. This work explores the use of self-supervised contrastive learning to the simultaneous detection of two types of OOD samples: unseen classes and adversarial perturbations. First, we pair self-supervised contrastive learning with the maximum mean discrepancy (MMD) two-sample test. This approach enables us to robustly test whether two independent sets of samples originate from the same distribution, and we demonstrate its effectiveness by discriminating between CIFAR-10 and CIFAR-10.1 with higher confidence than previous work. Motivated by this success, we introduce CADet (Contrastive Anomaly Detection), a novel method for OOD detection of single samples. CADet draws inspiration from MMD, but leverages the similarity between contrastive transformations of a same sample. CADet outperforms existing adversarial detection methods in identifying adversarially perturbed samples on ImageNet and achieves comparable performance to unseen label detection methods on two challenging benchmarks: ImageNet-O and iNaturalist. Significantly, CADet is fully self-supervised and requires neither labels for in-distribution samples nor access to OOD examples.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 57 of its 75 references that are in the map. First posted on arXiv 4 Oct 2022.

Builds on

57 of 75 references.

References · 57

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  7. 2016Density estimation using Real NVPcited by 2,029
  8. 2018Unsupervised Feature Learning via Non-Parametric Instance-level Discriminationcited by 1,838
  9. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  10. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  11. 2019Natural Adversarial Examplescited by 1,401
  12. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
38 more
  1. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  2. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  3. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  4. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  5. 2017Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discoverycited by 566
  6. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  7. 2017Large Batch Training of Convolutional Networkscited by 529
  8. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  9. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  10. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
  11. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  12. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  13. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  14. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  15. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  16. 2019Your Classifier is Secretly an Energy Based Model and You Should Treat it Like Onecited by 402
  17. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  18. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  19. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  20. 2017Detecting Adversarial Samples from Artifactscited by 244
  21. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  22. 2017On Detecting Adversarial Perturbationscited by 232
  23. 2020Classification-Based Anomaly Detection for General Datacited by 210
  24. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 203
  25. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  26. 2019Input complexity and out-of-distribution detection with likelihood-based generative modelscited by 186
  27. 2020Contrastive Training for Improved Out-of-Distribution Detectioncited by 186
  28. 2020Learning and Evaluating Representations for Deep One-class Classificationcited by 133
  29. 2020Learning Deep Kernels for Non-Parametric Two-Sample Testscited by 129
  30. 2016Deep Structured Energy Based Models for Anomaly Detectioncited by 113
  31. 2016Generative Models and Model Criticism via Optimized Maximum Mean Discrepancycited by 99
  32. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  33. 2016Interpretable Distribution Features with Maximum Testing Powercited by 63
  34. 2015Fast Two-Sample Testing with Analytic Representations of Probability Measurescited by 53
  35. 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
  36. 2020Maximum Mean Discrepancy Test is Aware of Adversarial Attackscited by 44
  37. 2021Neural Mean Discrepancy for Efficient Out-of-Distribution Detectioncited by 42
  38. 2018Learning deep kernels for exponential family densitiescited by 36

50 most cited of 57 All 57 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 6; 2026: 1.

11 papers.

  1. 2025FruitNeRF++: A Generalized Multi-Fruit Counting Method Utilizing Contrastive Learning and Neural Radiance Fieldscited by 4
  2. 2023Expecting The Unexpected: Towards Broad Out-Of-Distribution Detectioncited by 3
  3. 2025Can We Ignore Labels In Out of Distribution Detection?cited by 3
  4. 2024Evaluating Self-Supervised Learning in Medical Imaging: A Benchmark for Robustness, Generalizability, and Multi-Domain Impactcited by 2
  5. 2025AutoSciDACT: Automated Scientific Discovery through Contrastive Embedding and Hypothesis Testingcited by 2
  6. 2024Deep Metric Learning-Based Out-of-Distribution Detection with Synthetic Outlier Exposurecited by 0
  7. 2024Resultant: Incremental Effectiveness on Likelihood for Unsupervised Out-of-Distribution Detectioncited by 0
  8. 2025DynaSubVAE: Adaptive Subgrouping for Scalable and Robust OOD Detectioncited by 0
  9. 2025KoALA: KL-L0 Adversarial Detector via Label Agreementcited by 0
  10. 2025CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detectioncited by 0
  11. 2026LOTTERY: Learning from Reference-Only Samples in Two-Sample Testing under Size Asymmetrycited by 0