mlsanityData to 14 Oct 2026

Exploiting Vision Language Model for Training-Free 3D Point Cloud OOD Detection via Graph Score Propagation

arXiv 2506.22375 ↗First posted 27 Jun 2025cs.CVcited by 0

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

Abstract (arXiv)

Out-of-distribution (OOD) detection in 3D point cloud data remains a challenge, particularly in applications where safe and robust perception is critical. While existing OOD detection methods have shown progress for 2D image data, extending these to 3D environments involves unique obstacles. This paper introduces a training-free framework that leverages Vision-Language Models (VLMs) for effective OOD detection in 3D point clouds. By constructing a graph based on class prototypes and testing data, we exploit the data manifold structure to enhancing the effectiveness of VLMs for 3D OOD detection. We propose a novel Graph Score Propagation (GSP) method that incorporates prompt clustering and self-training negative prompting to improve OOD scoring with VLM. Our method is also adaptable to few-shot scenarios, providing options for practical applications. We demonstrate that GSP consistently outperforms state-of-the-art methods across synthetic and real-world datasets 3D point cloud OOD detection.

Key facts. No citing papers in the map yet (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 51 of its 64 references that are in the map. First posted on arXiv 27 Jun 2025.

Builds on

51 of 64 references.

Closest ancestors · 6

Same direction, newest first

  1. 2024Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model24 Dec
  2. 2024Label Propagation for Zero-shot Classification with Vision-Language Models5 Apr
  3. 2024Negative Label Guided OOD Detection with Pretrained Vision-Language Models29 Mar
  4. 2023ArGue: Attribute-Guided Prompt Tuning for Vision-Language Models27 Nov
  5. 2023ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation4 Aug
  6. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification19 Jul

Other references · 45

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  3. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,322
  4. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,864
  5. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  6. 2020Supervised Contrastive Learningcited by 2,829
  7. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,385
  8. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
  9. 2020Energy-based Out-of-distribution Detectioncited by 1,299
  10. 2018Deep Anomaly Detection with Outlier Exposurecited by 942
  11. 2021Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modelingcited by 653
  12. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
33 more
  1. 2019Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Datacited by 532
  2. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  3. 2021ReAct: Out-of-distribution Detection With Rectified Activationscited by 486
  4. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 463
  5. 2021Open-Set Recognition: a Good Closed-Set Classifier is All You Need?cited by 353
  6. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 339
  7. 2019Label Propagation for Deep Semi-supervised Learningcited by 289
  8. 2022ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understandingcited by 267
  9. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 216
  10. 2023ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understandingcited by 202
  11. 2022CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-trainingcited by 160
  12. 2021Adversarial Reciprocal Points Learning for Open Set Recognitioncited by 153
  13. 2023CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say Nocited by 130
  14. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  15. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  16. 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 80
  17. 2022Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptionscited by 80
  18. 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
  19. 2023DePT: Decoupled Prompt Tuningcited by 58
  20. 2021A Theory of Label Propagation for Subpopulation Shiftcited by 48
  21. 2023Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Needcited by 46
  22. 2024Learning Transferable Negative Prompts for Out-of-Distribution Detectioncited by 43
  23. 2023NECO: NEural Collapse Based Out-of-distribution detectioncited by 42
  24. 2023ID-like Prompt Learning for Few-Shot Out-of-Distribution Detectioncited by 42
  25. 2023Learning to Augment Distributions for Out-of-Distribution Detectioncited by 38
  26. 2020Out-of-Distribution Detection for Automotive Perceptioncited by 37
  27. 2023Toward Unsupervised 3D Point Cloud Anomaly Detection using Variational Autoencodercited by 18
  28. 2025Reliable Few-shot Learning under Dual Noisescited by 17
  29. 2023Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understandingcited by 13
  30. 20223DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Cloudscited by 11
  31. 2024Revisiting Out-of-Distribution Detection in LiDAR-based 3D Object Detectioncited by 11
  32. 2022Label Propagation with Weak Supervisioncited by 9
  33. 2023Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagationcited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation
  2. 2023Open-Vocabulary Point-Cloud Object Detection without 3D Annotation
  3. 2025An Empirical Analysis of VLM-based OOD Detection: Mechanisms, Advantages, and Sensitivity
  4. 2026ALOOD: Exploiting Language Representations for LiDAR-based Out-of-Distribution Object Detection
  5. 2025A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models
  6. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey
  7. 2025GLIP-OOD: Zero-Shot Graph OOD Detection with Graph Foundation Model
  8. 2025VisTa: Visual-contextual and Text-augmented Zero-shot Object-level OOD Detection