mlsanityData to 7 Oct 2026

CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instances

arXiv 2007.08176 ↗First posted 16 Jul 2020cs.LG stat.MLcited by 441

Not on the map. Why?

Abstract (arXiv)

Novelty detection, i.e., identifying whether a given sample is drawn from outside the training distribution, is essential for reliable machine learning. To this end, there have been many attempts at learning a representation well-suited for novelty detection and designing a score based on such representation. In this paper, we propose a simple, yet effective method named contrasting shifted instances (CSI), inspired by the recent success on contrastive learning of visual representations. Specifically, in addition to contrasting a given sample with other instances as in conventional contrastive learning methods, our training scheme contrasts the sample with distributionally-shifted augmentations of itself. Based on this, we propose a new detection score that is specific to the proposed training scheme. Our experiments demonstrate the superiority of our method under various novelty detection scenarios, including unlabeled one-class, unlabeled multi-class and labeled multi-class settings, with various image benchmark datasets. Code and pre-trained models are available at https://github.com/alinlab/CSI.

Key facts. Cited by 441 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 78; 2022: 97; 2023: 101; 2024: 73; 2025: 64; 2026: 28.

441 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  2. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  3. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  4. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 397
  5. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  6. 2022The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Modelscited by 312
  7. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  8. 2021Unsolved Problems in ML Safetycited by 291
  9. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  10. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  11. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 251
  12. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
38 more
  1. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  2. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  3. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  4. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
  5. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  6. 2023Non-Parametric Outlier Synthesiscited by 129
  7. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  8. 2021Fully Convolutional Cross-Scale-Flows for Image-based Defect Detectioncited by 117
  9. 2022Catching Both Gray and Black Swans: Open-set Supervised Anomaly Detectioncited by 104
  10. 2021OVANet: One-vs-All Network for Universal Domain Adaptationcited by 92
  11. 2022Back to the Feature: Classical 3D Features are (Almost) All You Need for 3D Anomaly Detectioncited by 92
  12. 2021Mean-Shifted Contrastive Loss for Anomaly Detectioncited by 87
  13. 2022Training OOD Detectors in their Natural Habitatscited by 86
  14. 2022Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detectioncited by 79
  15. 2022A Theoretical Study on Solving Continual Learningcited by 78
  16. 2023Dream the Impossible: Outlier Imagination with Diffusion Modelscited by 77
  17. 2022Explicit Boundary Guided Semi-Push-Pull Contrastive Learning for Supervised Anomaly Detectioncited by 72
  18. 2021Contrastive Out-of-Distribution Detection for Pretrained Transformerscited by 70
  19. 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 70
  20. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  21. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  22. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Modelscited by 66
  23. 2021Mixture Outlier Exposure: Towards Out-of-Distribution Detection in Fine-grained Environmentscited by 65
  24. 2023Unsupervised Out-of-Distribution Detection with Diffusion Inpaintingcited by 57
  25. 2022RankFeat: Rank-1 Feature Removal for Out-of-distribution Detectioncited by 52
  26. 2024On Large Language Model Continual Unlearningcited by 51
  27. 2021SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustnesscited by 49
  28. 2022SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakescited by 49
  29. 2023Fast Decision Boundary based Out-of-Distribution Detectorcited by 48
  30. 2023Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Needcited by 46
  31. 2021Detecting Outliers with Poisson Image Interpolationcited by 44
  32. 2022Towards Open-Set Object Detection and Discoverycited by 44
  33. 2021OpenMatch: Open-set Consistency Regularization for Semi-supervised Learning with Outlierscited by 43
  34. 2024Learning with Mixture of Prototypes for Out-of-Distribution Detectioncited by 43
  35. 2023Out-of-distribution Detection with Implicit Outlier Transformationcited by 42
  36. 2023How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?cited by 38
  37. 2023Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolationcited by 38
  38. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38

50 most cited of 441 All 441 (JSON)