mlsanityData to 7 Oct 2026

CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring

arXiv 2405.14737 ↗First posted 23 May 2024cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Detection of out-of-distribution (OOD) samples is crucial for safe real-world deployment of machine learning models. Recent advances in vision language foundation models have made them capable of detecting OOD samples without requiring in-distribution (ID) images. However, these zero-shot methods often underperform as they do not adequately consider ID class likelihoods in their detection confidence scoring. Hence, we introduce CLIPScope, a zero-shot OOD detection approach that normalizes the confidence score of a sample by class likelihoods, akin to a Bayesian posterior update. Furthermore, CLIPScope incorporates a novel strategy to mine OOD classes from a large lexical database. It selects class labels that are farthest and nearest to ID classes in terms of CLIP embedding distance to maximize coverage of OOD samples. We conduct extensive ablation studies and empirical evaluations, demonstrating state of the art performance of CLIPScope across various OOD detection benchmarks.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 23 May 2024.

Builds on

29 of 44 references.

References · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  3. 2013Describing Textures in the Wildcited by 2,110
  4. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  5. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  6. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  7. 2019Natural Adversarial Examplescited by 1,401
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  10. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  11. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  12. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
17 more
  1. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  2. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  3. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  4. 2019Deep Semi-Supervised Anomaly Detectioncited by 290
  5. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  6. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  7. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  8. 2020PANDA: Adapting Pretrained Features for Anomaly Detection and Segmentationcited by 175
  9. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  10. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
  11. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  12. 2023Non-Parametric Outlier Synthesiscited by 129
  13. 2023CLIPood: Generalizing CLIP to Out-of-Distributionscited by 96
  14. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Modelscited by 66
  15. 2020Backpropagated Gradient Representations for Anomaly Detectioncited by 54
  16. 2022Latent Outlier Exposure for Anomaly Detection with Contaminated Datacited by 48
  17. 2023Differential Analysis of Triggers and Benign Features for Black-Box DNN Backdoor Detectioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 6; 2025: 3; 2026: 4.

13 papers.

Sort:

By area:

  1. 2024Large Language Models for Anomaly and Out-of-Distribution Detection: A Surveycited by 24
  2. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 24
  3. 2024Post-hoc Probabilistic Vision-Language Modelscited by 13
  4. 2024CMOOD: Concept-based Multi-label OOD Detectioncited by 6
  5. 2024Mamba Fusion: Learning Actions Through Questioningcited by 5
  6. 2024BayesAdapter: enhanced uncertainty estimation in CLIP few-shot adaptationcited by 3
  7. 2025Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimationcited by 3
  8. 2026Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Modelscited by 2
  9. 2026Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMscited by 1
  10. 2025Prompt Optimization Meets Subspace Representation Learning for Few-shot Out-of-Distribution Detectioncited by 0
  11. 2025ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corporacited by 0
  12. 2026TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detectioncited by 0
1 more
  1. 2026Training-Free Out-of-Distribution Detection for Pathology Whole-Slide Imagescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CLIP-driven Outliers Synthesis for few-shot OOD detection
  2. 2025COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP
  3. 2024Zero-Shot Out-of-Distribution Detection with Outlier Label Exposure
  4. 2025VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection
  5. 2025Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection
  6. 2025Recent Advances in Out-of-Distribution Detection with CLIP-Like Models: A Survey
  7. 2025NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection
  8. 2025A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models