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

arXiv: https://arxiv.org/abs/2304.04521 · HTML: https://mlsanity.com/paper/2304.04521/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 51 references that are in the map.
- First posted on arXiv 10 Apr 2023.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [Learning to Prompt for Vision-Language Models](https://mlsanity.com/paper/2109.01134/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networks](https://mlsanity.com/paper/1706.02690/) (2017)
- [Energy-based Out-of-distribution Detection](https://mlsanity.com/paper/2010.03759/) (2020)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [Out-of-Distribution Detection with Deep Nearest Neighbors](https://mlsanity.com/paper/2204.06507/) (2022)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Scaling Out-of-Distribution Detection for Real-World Settings](https://mlsanity.com/paper/1911.11132/) (2019)
- [Do Deep Generative Models Know What They Don't Know?](https://mlsanity.com/paper/1810.09136/) (2018)
- [ViM: Out-Of-Distribution with Virtual-logit Matching](https://mlsanity.com/paper/2203.10807/) (2022)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [On the Importance of Gradients for Detecting Distributional Shifts in the Wild](https://mlsanity.com/paper/2110.00218/) (2021)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [Pretrained Transformers Improve Out-of-Distribution Robustness](https://mlsanity.com/paper/2004.06100/) (2020)
- [Exploring the Limits of Out-of-Distribution Detection](https://mlsanity.com/paper/2106.03004/) (2021)
- [OpenOOD: Benchmarking Generalized Out-of-Distribution Detection](https://mlsanity.com/paper/2210.07242/) (2022)
- [MOS: Towards Scaling Out-of-distribution Detection for Large Semantic Space](https://mlsanity.com/paper/2105.01879/) (2021)
- [Why Normalizing Flows Fail to Detect Out-of-Distribution Data](https://mlsanity.com/paper/2006.08545/) (2020)
- [Delving into Out-of-Distribution Detection with Vision-Language Representations](https://mlsanity.com/paper/2211.13445/) (2022)
- [Generative OpenMax for Multi-Class Open Set Classification](https://mlsanity.com/paper/1707.07418/) (2017)
- [Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP](https://mlsanity.com/paper/2109.02748/) (2021)
- [C2AE: Class Conditioned Auto-Encoder for Open-set Recognition](https://mlsanity.com/paper/1904.01198/) (2019)
- [Non-Parametric Outlier Synthesis](https://mlsanity.com/paper/2303.02966/) (2023)

## Built on by (most cited first, 30 of 36)

- [LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning](https://mlsanity.com/paper/2306.01293/) (2023)
- [Generalized Out-of-Distribution Detection and Beyond in Vision Language Model Era: A Survey](https://mlsanity.com/paper/2407.21794/) (2024)
- [GalLoP: Learning Global and Local Prompts for Vision-Language Models](https://mlsanity.com/paper/2407.01400/) (2024)
- [Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection](https://mlsanity.com/paper/2411.03359/) (2024)
- [Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper](https://mlsanity.com/paper/2511.04583/) (2025)
- [Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detection](https://mlsanity.com/paper/2506.17633/) (2025)
- [Exploiting Diffusion Prior for Out-of-Distribution Detection](https://mlsanity.com/paper/2406.11105/) (2024)
- [Mysteries of the Deep: Role of Intermediate Representations in Out of Distribution Detection](https://mlsanity.com/paper/2510.05782/) (2025)
- [Likelihood-Aware Semantic Alignment for Full-Spectrum Out-of-Distribution Detection](https://mlsanity.com/paper/2312.01732/) (2023)
- [Zero-Shot Out-of-Distribution Detection with Outlier Label Exposure](https://mlsanity.com/paper/2406.01170/) (2024)
- [Delving into Out-of-Distribution Detection with Medical Vision-Language Models](https://mlsanity.com/paper/2503.01020/) (2025)
- [Can Pre-trained Networks Detect Familiar Out-of-Distribution Data?](https://mlsanity.com/paper/2310.00847/) (2023)
- [Dual-Adapter: Training-free Dual Adaptation for Few-shot Out-of-Distribution Detection](https://mlsanity.com/paper/2405.16146/) (2024)
- [Revisiting Logit Distributions for Reliable Out-of-Distribution Detection](https://mlsanity.com/paper/2510.20134/) (2025)
- [A Benchmark and Evaluation for Real-World Out-of-Distribution Detection Using Vision-Language Models](https://mlsanity.com/paper/2501.18463/) (2025)
- [T-QPM: Enabling Temporal Out-Of-Distribution Detection and Domain Generalization for Vision-Language Models in Open-World](https://mlsanity.com/paper/2603.18481/) (2026)
- [OpenEarthSensing: Large-Scale Fine-Grained Benchmark for Open-World Remote Sensing](https://mlsanity.com/paper/2502.20668/) (2025)
- [NegRefine: Refining Negative Label-Based Zero-Shot OOD Detection](https://mlsanity.com/paper/2507.09795/) (2025)
- [TTL: Test-time Textual Learning for OOD Detection with Pretrained Vision-Language Models](https://mlsanity.com/paper/2604.15756/) (2026)
- [Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting](https://mlsanity.com/paper/2402.03292/) (2024)
- [Generalized Few-Shot Out-of-Distribution Detection](https://mlsanity.com/paper/2508.05732/) (2025)
- [ICONIC-444: A 3.1-Million-Image Dataset for OOD Detection Research](https://mlsanity.com/paper/2601.10802/) (2026)
- [Geometry-Aware Dataset Condensation for Diffusion Model Training](https://mlsanity.com/paper/2606.05883/) (2026)
- [Concept Matching with Agent for Out-of-Distribution Detection](https://mlsanity.com/paper/2405.16766/) (2024)
- [COOkeD: Ensemble-based OOD detection in the era of zero-shot CLIP](https://mlsanity.com/paper/2507.22576/) (2025)
- [OpenHAIV: A Framework Towards Practical Open-World Learning](https://mlsanity.com/paper/2508.07270/) (2025)
- [Prompt Optimization Meets Subspace Representation Learning for Few-shot Out-of-Distribution Detection](https://mlsanity.com/paper/2509.18111/) (2025)
- [Enhancing Few-Shot Out-of-Distribution Detection via the Refinement of Foreground and Background](https://mlsanity.com/paper/2601.15065/) (2026)
- [Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysis](https://mlsanity.com/paper/2602.01127/) (2026)
- [Local-Global Prompt Learning via Sparse Optimal Transport](https://mlsanity.com/paper/2603.08347/) (2026)

## 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.