mlsanityData to 14 Oct 2026

Learning Transferable Negative Prompts for Out-of-Distribution Detection

arXiv 2404.03248 ↗First posted 4 Apr 2024cs.CVcited by 43

Not on the map. Why?

Abstract (arXiv)

Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate. To address this issue, we introduce a novel OOD detection method, named 'NegPrompt', to learn a set of negative prompts, each representing a negative connotation of a given class label, for delineating the boundaries between ID and OOD images. It learns such negative prompts with ID data only, without any reliance on external outlier data. Further, current methods assume the availability of samples of all ID classes, rendering them ineffective in open-vocabulary learning scenarios where the inference stage can contain novel ID classes not present during training. In contrast, our learned negative prompts are transferable to novel class labels. Experiments on various ImageNet benchmarks show that NegPrompt surpasses state-of-the-art prompt-learning-based OOD detection methods and maintains a consistent lead in hard OOD detection in closed- and open-vocabulary classification scenarios. Code is available at https://github.com/mala-lab/negprompt.

Key facts. Cited by 43 papers in the map (data through 14 Oct 2026). Builds on 46 of its 56 references that are in the map. First posted on arXiv 4 Apr 2024.

Builds on

46 of 56 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  5. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  6. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  7. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,386
  8. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  9. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,152
  10. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  11. 2020Supervised Contrastive Learningcited by 2,829
  12. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
34 more
  1. 2021Learning to Prompt for Vision-Language Modelscited by 2,281
  2. 2013Describing Textures in the Wildcited by 2,125
  3. 2022Visual Prompt Tuningcited by 1,681
  4. 2022Conditional Prompt Learning for Vision-Language Modelscited by 1,433
  5. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  6. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  7. 2021CLIP-Adapter: Better Vision-Language Models with Feature Adapterscited by 1,026
  8. 2019How Can We Know What Language Models Know?cited by 959
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  10. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  11. 2022MaPLe: Multi-modal Prompt Learningcited by 687
  12. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  13. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  14. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 405
  15. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  16. 2021Factual Probing Is [MASK]: Learning vs. Learning to Recallcited by 291
  17. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  18. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  19. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  20. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 152
  21. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  22. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  23. 2023VadCLIP: Adapting Vision-Language Models for Weakly Supervised Video Anomaly Detectioncited by 123
  24. 2021Learning Placeholders for Open-Set Recognitioncited by 121
  25. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  26. 2022DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotationscited by 102
  27. 2024Toward Generalist Anomaly Detection via In-context Residual Learning with Few-shot Sample Promptscited by 89
  28. 2021Pixel-wise Energy-biased Abstention Learning for Anomaly Segmentation on Complex Urban Driving Scenescited by 83
  29. 2022Residual Pattern Learning for Pixel-wise Out-of-Distribution Detection in Semantic Segmentationcited by 55
  30. 2023Out-of-Distribution Detection in Long-Tailed Recognition with Calibrated Outlier Class Learningcited by 23
  31. 2023DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotationscited by 22
  32. 2023Simple Image-level Classification Improves Open-vocabulary Object Detectioncited by 15
  33. 2023Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worldscited by 11
  34. 2022Large-Scale Open-Set Classification Protocols for ImageNetcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 10; 2025: 23; 2026: 10.

43 papers.

Sort:

By area:

  1. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  2. 2024Out-of-Distribution Detection: A Task-Oriented Survey of Recent Advancescited by 26
  3. 2024AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Modelscited by 16
  4. 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 15
  5. 2025CountGD++: Generalized Prompting for Open-World Countingcited by 8
  6. 2024OpenCIL: Benchmarking Out-of-Distribution Detection in Class-Incremental Learningcited by 7
  7. 2025Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detectioncited by 7
  8. 2025Recent Advances in Out-of-Distribution Detection with CLIP-Like Models: A Surveycited by 6
  9. 2024Zero-Shot Out-of-Distribution Detection with Outlier Label Exposurecited by 5
  10. 2024From Open Vocabulary to Open World: Teaching Vision Language Models to Detect Novel Objectscited by 5
  11. 2025Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detectioncited by 5
  12. 2025Revisiting Logit Distributions for Reliable Out-of-Distribution Detectioncited by 4
31 more
  1. 2024Boosting Few-Shot Open-Set Object Detection via Prompt Learning and Robust Decision Boundarycited by 3
  2. 2025A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Modelscited by 3
  3. 2025Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimationcited by 3
  4. 2025FA: Forced Prompt Learning of Vision-Language Models for Out-of-Distribution Detectioncited by 3
  5. 2026T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-Worldcited by 3
  6. 2025NegRefine: Refining Negative Label-Based Zero-Shot OOD Detectioncited by 2
  7. 2025Hierarchical Vision-Language Learning for Medical Out-of-Distribution Detectioncited by 2
  8. 2025Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systemscited by 2
  9. 2026TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Modelscited by 2
  10. 2025LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Datacited by 1
  11. 2025Unlearning the Noisy Correspondence Makes CLIP More Robustcited by 1
  12. 2025Generalized Few-Shot Out-of-Distribution Detectioncited by 1
  13. 2025An Empirical Analysis of VLM-based OOD Detection: Mechanisms, Advantages, and Sensitivitycited by 1
  14. 2025Delta Energy: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalizationcited by 1
  15. 2026EraseAnything++: Enabling Concept Erasure in Rectified Flow Transformers Leveraging Multi-Object Optimizationcited by 1
  16. 2026Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMscited by 1
  17. 2026PROBE: Diagnosing Residual Concept Capacity in Erased Text-to-Video Diffusion Modelscited by 1
  18. 2026Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Modelscited by 1
  19. 2026Where Concept Erasure Should Occur: Concept-Layer Alignment in Text-to-Video Diffusion Modelscited by 1
  20. 2024Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognitioncited by 0
  21. 2024Concept Matching with Agent for Out-of-Distribution Detectioncited by 0
  22. 2025ULFine: Unbiased Lightweight Fine-tuning for Foundation-Model-Assisted Long-Tailed Semi-Supervised Learningcited by 0
  23. 2025Informed Mixing -- Improving Open Set Recognition via Attribution-based Augmentationcited by 0
  24. 2025Dual-Path Stable Soft Prompt Generation for Domain Generalizationcited by 0
  25. 2025The Devil is in the Darkness: Diffusion-Based Nighttime Dehazing Anchored in Brightness Perceptioncited by 0
  26. 2025Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagationcited by 0
  27. 2025Prompt Optimization Meets Subspace Representation Learning for Few-shot Out-of-Distribution Detectioncited by 0
  28. 2025ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corporacited by 0
  29. 2026Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Modelscited by 0
  30. 2026NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Modelscited by 0
  31. 2026Not All Layers Are Equal: Dynamic Layer Routing for Reliable CLIP OOD Detectioncited by 0