mlsanityData to 14 Oct 2026

NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection

arXiv 2507.09795 ↗First posted 13 Jul 2025cs.CV cs.LGcited by 2

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

Abstract (arXiv)

Recent advancements in Vision-Language Models like CLIP have enabled zero-shot OOD detection by leveraging both image and textual label information. Among these, negative label-based methods such as NegLabel and CSP have shown promising results by utilizing a lexicon of words to define negative labels for distinguishing OOD samples. However, these methods suffer from detecting in-distribution samples as OOD due to negative labels that are subcategories of in-distribution labels or proper nouns. They also face limitations in handling images that match multiple in-distribution and negative labels. We propose NegRefine, a novel negative label refinement framework for zero-shot OOD detection. By introducing a filtering mechanism to exclude subcategory labels and proper nouns from the negative label set and incorporating a multi-matching-aware scoring function that dynamically adjusts the contributions of multiple labels matching an image, NegRefine ensures a more robust separation between in-distribution and OOD samples. We evaluate NegRefine on large-scale benchmarks, including ImageNet-1K. The code is available at https://github.com/ah-ansari/NegRefine.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 31 of its 43 references that are in the map. First posted on arXiv 13 Jul 2025.

Builds on

31 of 43 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models26 Oct
  2. 2024LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models12 Jul
  3. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Models29 Mar

Other references · 28

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023Qwen Technical Reportcited by 3,344
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  4. 2013Describing Textures in the Wildcited by 2,125
  5. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,850
  6. 2019Natural Adversarial Examplescited by 1,408
  7. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  8. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  9. 2019Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalizationcited by 1,247
  10. 2023A Survey on Evaluation of Large Language Modelscited by 1,242
  11. 2019Learning Robust Global Representations by Penalizing Local Predictive Powercited by 1,013
  12. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
16 more
  1. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  2. 2023A Comprehensive Overview of Large Language Modelscited by 648
  3. 2021Extract Free Dense Labels from CLIPcited by 583
  4. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  5. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  6. 2022Mitigating Neural Network Overconfidence with Logit Normalizationcited by 252
  7. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  8. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  9. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 152
  10. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 134
  11. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  12. 2023Non-Parametric Outlier Synthesiscited by 129
  13. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  14. 2021On the Impact of Spurious Correlation for Out-of-distribution Detectioncited by 68
  15. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  16. 2023GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detectioncited by 36

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Modelscited by 2
  2. 2026DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CMOOD: Concept-based Multi-label OOD Detection
  2. 2026TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detection
  3. 2024Zero-Shot Out-of-Distribution Detection with Outlier Label Exposure
  4. 2025ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning
  5. 2025Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection
  6. 2024CLIPScope: Enhancing Zero-Shot OOD Detection with Bayesian Scoring
  7. 2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
  8. 2026Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Models