mlsanityData to 7 Oct 2026

AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models

arXiv 2410.20149 ↗First posted 26 Oct 2024cs.CV cs.AI cs.LGcited by 16

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

Abstract (arXiv)

Recent research has shown that pre-trained vision-language models are effective at identifying out-of-distribution (OOD) samples by using negative labels as guidance. However, employing consistent negative labels across different OOD datasets often results in semantic misalignments, as these text labels may not accurately reflect the actual space of OOD images. To overcome this issue, we introduce textitadaptive negative proxies, which are dynamically generated during testing by exploring actual OOD images, to align more closely with the underlying OOD label space and enhance the efficacy of negative proxy guidance. Specifically, our approach utilizes a feature memory bank to selectively cache discriminative features from test images, representing the targeted OOD distribution. This facilitates the creation of proxies that can better align with specific OOD datasets. While task-adaptive proxies average features to reflect the unique characteristics of each dataset, the sample-adaptive proxies weight features based on their similarity to individual test samples, exploring detailed sample-level nuances. The final score for identifying OOD samples integrates static negative labels with our proposed adaptive proxies, effectively combining textual and visual knowledge for enhanced performance. Our method is training-free and annotation-free, and it maintains fast testing speed. Extensive experiments across various benchmarks demonstrate the effectiveness of our approach, abbreviated as AdaNeg. Notably, on the large-scale ImageNet benchmark, our AdaNeg significantly outperforms existing methods, with a 2.45% increase in AUROC and a 6.48% reduction in FPR95. Codes are available at urlhttps://github.com/YBZh/OpenOOD-VLM.

Key facts. Cited by 16 papers in the map (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 57 of its 79 references that are in the map. First posted on arXiv 26 Oct 2024.

Builds on

57 of 79 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024LAPT: Label-driven Automated Prompt Tuning for OOD Detection with Vision-Language Models12 Jul
  2. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Models29 Mar
  3. 2024Dual Memory Networks: A Versatile Adaptation Approach for Vision-Language Models26 Mar
  4. 2023How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?9 Jun
  5. 2022Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models15 Sep

Other references · 52

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  4. 2013Describing Textures in the Wildcited by 2,110
  5. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  6. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  7. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  8. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  9. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  10. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  11. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  12. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
38 more
  1. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  2. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  3. 2020CSI: Novelty Detection via Contrastive Learning on Distributionally Shifted Instancescited by 441
  4. 2019Video Object Segmentation using Space-Time Memory Networkscited by 436
  5. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  6. 2014Memory Networkscited by 354
  7. 2023A Comprehensive Survey on Test-Time Adaptation under Distribution Shiftscited by 353
  8. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 351
  9. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  10. 2022VOS: Learning What You Don't Know by Virtual Outlier Synthesiscited by 300
  11. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  12. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  13. 2021SSD: A Unified Framework for Self-Supervised Outlier Detectioncited by 264
  14. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  15. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  16. 2022Extremely Simple Activation Shaping for Out-of-Distribution Detectioncited by 212
  17. 2021A Simple Fix to Mahalanobis Distance for Improving Near-OOD Detectioncited by 206
  18. 2023OpenOOD v1.5: Enhanced Benchmark for Out-of-Distribution Detectioncited by 178
  19. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
  20. 2021OpenGAN: Open-Set Recognition via Open Data Generationcited by 135
  21. 2023In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluationcited by 132
  22. 2021PixMix: Dreamlike Pictures Comprehensively Improve Safety Measurescited by 131
  23. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  24. 2023Non-Parametric Outlier Synthesiscited by 129
  25. 2020Memory Enhanced Global-Local Aggregation for Video Object Detectioncited by 128
  26. 2022How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?cited by 128
  27. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  28. 2020BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19 patientscited by 81
  29. 2023Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancementcited by 77
  30. 2022Unknown-Aware Object Detection: Learning What You Don't Know from Videos in the Wildcited by 70
  31. 2021Energy-Based Open-World Uncertainty Modeling for Confidence Calibrationcited by 46
  32. 2020Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practicecited by 43
  33. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  34. 2023ID-like Prompt Learning for Few-Shot Out-of-Distribution Detectioncited by 42
  35. 2020Robust High-dimensional Memory-augmented Neural Networkscited by 31
  36. 2022Relation Matters: Foreground-aware Graph-based Relational Reasoning for Domain Adaptive Object Detectioncited by 17
  37. 2023ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentationcited by 14
  38. 2023AUTO: Adaptive Outlier Optimization for Test-Time OOD Detectioncited by 12

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 9; 2026: 7.

16 papers.

Sort:

By area:

  1. 2025Recent Advances in Out-of-Distribution Detection with CLIP-Like Models: A Surveycited by 5
  2. 2025Knowledge Regularized Negative Feature Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 4
  3. 2025Mitigating the Modality Gap: Few-Shot Out-of-Distribution Detection with Multi-modal Prototypes and Image Bias Estimationcited by 3
  4. 2025Synthesizing Near-Boundary OOD Samples for Out-of-Distribution Detectioncited by 3
  5. 2025NegRefine: Refining Negative Label-Based Zero-Shot OOD Detectioncited by 2
  6. 2026TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Modelscited by 2
  7. 2025Delta Energy: Optimizing Energy Change During Vision-Language Alignment Improves both OOD Detection and OOD Generalizationcited by 1
  8. 2026Mind the Way You Select Negative Texts: Pursuing the Distance Consistency in OOD Detection with VLMscited by 1
  9. 2026Debiased Negative Mining Improves Out-of-distribution Detection with Pre-trained Vision-Language Modelscited by 1
  10. 2026Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMscited by 1
  11. 2025OpenHAIV: A Framework Towards Practical Open-World Learningcited by 0
  12. 2025Prompt Optimization Meets Subspace Representation Learning for Few-shot Out-of-Distribution Detectioncited by 0
4 more
  1. 2025ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corporacited by 0
  2. 2026Disentangled Graph Prompting for Out-Of-Distribution Detectioncited by 0
  3. 2026DynProto: Dynamic Prototype Evolution for Out-of-Distribution Detectioncited by 0
  4. 2026TINS: Test-time ID-prototype-separated Negative Semantics Learning for OOD Detectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models
  2. 2025ANTS: Adaptive Negative Textual Space Shaping for OOD Detection via Test-Time MLLM Understanding and Reasoning
  3. 2026Activation Matters: Test-time Activated Negative Labels for OOD Detection with Vision-Language Models
  4. 2025Out-of-Distribution Detection with Positive and Negative Prompt Supervision Using Large Language Models
  5. 2025Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection
  6. 2025SimLabel: Consistency-Guided OOD Detection with Pretrained Vision-Language Models
  7. 2024Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
  8. 2024CMOOD: Concept-based Multi-label OOD Detection