mlsanityData to 7 Oct 2026

ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corpora

arXiv 2511.07068 ↗First posted 10 Nov 2025cs.CV cs.LGcited by 0

On the map: Multimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP

Abstract (arXiv)

Large-scale visual out-of-distribution (OOD) detection has witnessed remarkable progress by leveraging vision-language models such as CLIP. However, a significant limitation of current methods is their reliance on a pre-defined set of in-distribution (ID) ground-truth label names (positives). These fixed label names can be unavailable, unreliable at scale, or become less relevant due to in-distribution shifts after deployment. Towards truly unsupervised OOD detection, we utilize widely available text corpora for positive label mining, bypassing the need for positives. In this paper, we utilize widely available text corpora for positive label mining under a general concept mining paradigm. Within this framework, we propose ClusterMine, a novel positive label mining method. ClusterMine is the first method to achieve state-of-the-art OOD detection performance without access to positive labels. It extracts positive concepts from a large text corpus by combining visual-only sample consistency (via clustering) and zero-shot image-text consistency. Our experimental study reveals that ClusterMine is scalable across a plethora of CLIP models and achieves state-of-the-art robustness to covariate in-distribution shifts. The code is available at https://github.com/HHU-MMBS/clustermine_wacv_official.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 58 of its 76 references that are in the map. First posted on arXiv 10 Nov 2025.

Builds on

58 of 76 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detection14 Jul
  2. 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models26 Oct
  3. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Models29 Mar
  4. 2023How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?9 Jun

Other references · 54

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 2020Scaling Laws for Neural Language Modelscited by 6,411
  5. 2017On Calibration of Modern Neural Networkscited by 4,860
  6. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  8. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  9. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  10. 2019Do ImageNet Classifiers Generalize to ImageNet?cited by 1,507
  11. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  12. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
38 more
  1. 2019Natural Adversarial Examplescited by 1,401
  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. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  5. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,163
  6. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,010
  7. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  8. 2021ImageNet-21K Pretraining for the Massescited by 607
  9. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 604
  10. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  11. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  12. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  13. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  14. 2020SCAN: Learning to Classify Images without Labelscited by 351
  15. 2020Are we done with ImageNet?cited by 329
  16. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  17. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  18. 2023Demystifying CLIP Datacited by 265
  19. 2023Data Filtering Networkscited by 247
  20. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  21. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  22. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 206
  23. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  24. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
  25. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  26. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  27. 2023Non-Parametric Outlier Synthesiscited by 129
  28. 2022Revisiting Weakly Supervised Pre-Training of Visual Perception Modelscited by 116
  29. 2021Can multi-label classification networks know what they don't know?cited by 100
  30. 2022Full-Spectrum Out-of-Distribution Detectioncited by 63
  31. 2023Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detectioncited by 57
  32. 2024Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approachcited by 48
  33. 2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46
  34. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  35. 2023Exploring the Limits of Deep Image Clustering using Pretrained Modelscited by 33
  36. 2023A framework for benchmarking class-out-of-distribution detection and its application to ImageNetcited by 31
  37. 2023ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithmscited by 22
  38. 2020Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shiftcited by 19

50 most cited of 54 All 54 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024CMOOD: Concept-based Multi-label OOD Detection
  2. 2025Recent Advances in Out-of-Distribution Detection with CLIP-Like Models: A Survey
  3. 2026Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models
  4. 2025SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models
  5. 2026DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detection
  6. 2025Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection
  7. 2026Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMs
  8. 2025NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection