mlsanityData to 7 Oct 2026

GL-MCM: Global and Local Maximum Concept Matching for Zero-Shot Out-of-Distribution Detection

arXiv 2304.04521 ↗First posted 10 Apr 2023cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Zero-shot out-of-distribution (OOD) detection is a task that detects OOD images during inference with only in-distribution (ID) class names. Existing methods assume ID images contain a single, centered object, and do not consider the more realistic multi-object scenarios, where both ID and OOD objects are present. To meet the needs of many users, the detection method must have the flexibility to adapt the type of ID images. To this end, we present Global-Local Maximum Concept Matching (GL-MCM), which incorporates local image scores as an auxiliary score to enhance the separability of global and local visual features. Due to the simple ensemble score function design, GL-MCM can control the type of ID images with a single weight parameter. Experiments on ImageNet and multi-object benchmarks demonstrate that GL-MCM outperforms baseline zero-shot methods and is comparable to fully supervised methods. Furthermore, GL-MCM offers strong flexibility in adjusting the target type of ID images. The code is available via https://github.com/AtsuMiyai/GL-MCM.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 36 of its 51 references that are in the map. First posted on arXiv 10 Apr 2023.

Builds on

36 of 51 references.

References · 36

  1. 2017Attention Is All You Needcited by 59,932
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  6. 2016A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networkscited by 2,362
  7. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  8. 2013Describing Textures in the Wildcited by 2,110
  9. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  10. 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
  11. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  12. 2021ImageNet-21K Pretraining for the Massescited by 607
24 more
  1. 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 596
  2. 2021Extract Free Dense Labels from CLIPcited by 580
  3. 2019Scaling Out-of-Distribution Detection for Real-World Settingscited by 465
  4. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  5. 2022ViM: Out-Of-Distribution with Virtual-logit Matchingcited by 404
  6. 2022Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classificationcited by 355
  7. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  8. 2023Side Adapter Network for Open-Vocabulary Semantic Segmentationcited by 296
  9. 2020Pretrained Transformers Improve Out-of-Distribution Robustnesscited by 293
  10. 2021Exploring the Limits of Out-of-Distribution Detectioncited by 283
  11. 2022OpenOOD: Benchmarking Generalized Out-of-Distribution Detectioncited by 267
  12. 2021MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Spacecited by 233
  13. 2020Why Normalizing Flows Fail to Detect Out-of-Distribution Datacited by 220
  14. 2022Delving into Out-of-Distribution Detection with Vision-Language Representationscited by 215
  15. 2017Generative OpenMax for Multi-Class Open Set Classificationcited by 157
  16. 2021Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIPcited by 151
  17. 2019C2AE: Class Conditioned Auto-Encoder for Open-set Recognitioncited by 142
  18. 2023Non-Parametric Outlier Synthesiscited by 129
  19. 2022ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehensioncited by 119
  20. 2022DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotationscited by 102
  21. 2021Can multi-label classification networks know what they don't know?cited by 100
  22. 2021Types of Out-of-Distribution Texts and How to Detect Themcited by 80
  23. 2021Revisiting Mahalanobis Distance for Transformer-Based Out-of-Domain Detectioncited by 67
  24. 2021Unsupervised Out-of-Domain Detection via Pre-trained Transformerscited by 31

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 8; 2025: 12; 2026: 13.

36 papers.

Sort:

By area:

  1. 2023LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learningcited by 107
  2. 2024Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Surveycited by 36
  3. 2024GalLoP: Learning Global and Local Prompts for Vision-Language Modelscited by 29
  4. 2024Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detectioncited by 15
  5. 2025Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Papercited by 10
  6. 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detectioncited by 8
  7. 2024Exploiting Diffusion Prior for Out-of-Distribution Detectioncited by 7
  8. 2025Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detectioncited by 6
  9. 2023Likelihood-Aware Semantic Alignment for Full-Spectrum Out-of-Distribution Detectioncited by 5
  10. 2024Zero-Shot Out-of-Distribution Detection with Outlier Label Exposurecited by 5
  11. 2025Delving into Out-of-Distribution Detection with Medical Vision-Language Modelscited by 5
  12. 2023Can Pre-trained Networks Detect Familiar Out-of-Distribution Data?cited by 4
24 more
  1. 2024Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detectioncited by 4
  2. 2025Revisiting Logit Distributions for Reliable Out-of-Distribution Detectioncited by 4
  3. 2025A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Modelscited by 3
  4. 2026T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-Worldcited by 3
  5. 2025OpenEarthSensing: Large-Scale Fine-Grained Benchmark for Open-World Remote Sensingcited by 2
  6. 2025NegRefine: Refining Negative Label-Based Zero-Shot OOD Detectioncited by 2
  7. 2026TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Modelscited by 2
  8. 2024Detecting Out-of-Distribution Objects through Class-Conditioned Inpaintingcited by 1
  9. 2025Generalized Few-Shot Out-of-Distribution Detectioncited by 1
  10. 2026ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Researchcited by 1
  11. 2026Geometry-Aware Dataset Condensation for Diffusion Model Trainingcited by 1
  12. 2024Concept Matching with Agent for Out-of-Distribution Detectioncited by 0
  13. 2025COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIPcited by 0
  14. 2025OpenHAIV: A Framework Towards Practical Open-World Learningcited by 0
  15. 2025Prompt Optimization Meets Subspace Representation Learning for Few-shot Out-of-Distribution Detectioncited by 0
  16. 2026Enhancing Few-Shot Out-of-Distribution Detection via the Refinement of Foreground and Backgroundcited by 0
  17. 2026Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysiscited by 0
  18. 2026Local-Global Prompt Learning via Sparse Optimal Transportcited by 0
  19. 2026GP-Adapter: Gaussian Process CLIP-Adapter for Few-Shot Out-of-Distribution Detectioncited by 0
  20. 2026PROTON: Prototype-Based Test-Time Online OOD Detection for Medical VLMscited by 0
  21. 2026Cross-Contextual Vision-Language Adaptation with LoRA for Personalized Severe Adverse Event Detection in Clinical Wound Monitoringcited by 0
  22. 2026Fi-ImageNet-1k: An OOD Benchmark From the Inside of the ImageNet-1k Validation Setcited by 0
  23. 2026SAM3-O2D2: Zero-Shot Object Out-of-Distribution Detection by Object Class Prompting of the SAM3-Image Modelcited by 0
  24. 2026Not All Layers Are Equal: Dynamic Layer Routing for Reliable CLIP OOD Detectioncited by 0