mlsanityData to 14 Oct 2026

H2VLR: Heterogeneous Hypergraph Vision-Language Reasoning for Few-Shot Anomaly Detection

arXiv 2604.14507 ↗First posted 16 Apr 2026cs.CV cs.LGcited by 0

On the map: LLM reasoning → Chain-of-thought reasoning for driving

Abstract (arXiv)

As a classic vision task, anomaly detection has been widely applied in industrial inspection and medical imaging. In this task, data scarcity is often a frequently-faced issue. To solve it, the few-shot anomaly detection (FSAD) scheme is attracting increasing attention. In recent years, beyond traditional visual paradigm, Vision-Language Model (VLM) has been extensively explored to boost this field. However, in currently-existing VLM-based FSAD schemes, almost all perform anomaly inference only by pairwise feature matching, ignoring structural dependencies and global consistency. To further redound to FSAD via VLM, we propose a Heterogeneous Hypergraph Vision-Language Reasoning (H2VLR) framework. It reformulates the FSAD as a high-order inference problem of visual-semantic relations, by jointly modeling visual regions and semantic concepts in a unified hypergraph. Experimental comparisons verify the effectiveness and advantages of H2VLR. It could often achieve state-of-the-art (SOTA) performance on representative industrial and medical benchmarks. Our code will be released upon acceptance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning. Builds on 22 of its 36 references that are in the map. First posted on arXiv 16 Apr 2026.

Builds on

22 of 36 references.

References · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  3. 2018Hypergraph Neural Networkscited by 488
  4. 2022SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentationcited by 400
  5. 2020Multiresolution Knowledge Distillation for Anomaly Detectioncited by 285
  6. 2023AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detectioncited by 271
  7. 2021VT-ADL: A Vision Transformer Network for Image Anomaly Detection and Localizationcited by 223
  8. 2022Registration based Few-Shot Anomaly Detectioncited by 133
  9. 2021UniGNN: a Unified Framework for Graph and Hypergraph Neural Networkscited by 130
  10. 2021You are AllSet: A Multiset Function Framework for Hypergraph Neural Networkscited by 127
  11. 2024PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detectioncited by 98
  12. 2023BMAD: Benchmarks for Medical Anomaly Detectioncited by 82
10 more
  1. 2025AA-CLIP: Enhancing Zero-shot Anomaly Detection via Anomaly-Aware CLIPcited by 73
  2. 2021A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detectioncited by 60
  3. 2025AdaptCLIP: Adapting CLIP for Universal Visual Anomaly Detectioncited by 29
  4. 2024UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detectioncited by 28
  5. 2024Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detectioncited by 22
  6. 2025Learning to Detect Multi-class Anomalies with Just One Normal Image Promptcited by 18
  7. 2025Hypergraph Vision Transformers: Images are More than Nodes, More than Edgescited by 16
  8. 2024Kernel-Aware Graph Prompt Learning for Few-Shot Anomaly Detectioncited by 15
  9. 2025DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookupcited by 10
  10. 2025One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detectioncited by 7

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models
  2. 2024VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection
  3. 2026Hypergraph Normal World Models for Logical Visual Anomaly Detection
  4. 2024VL4AD: Vision-Language Models Improve Pixel-wise Anomaly Detection
  5. 2025LogicAD: Explainable Anomaly Detection via VLM-based Text Feature Extraction
  6. 2026InspectorGPT: A Comparative Reasoning Enhanced VLM for Comprehensive Industrial Anomaly Detection
  7. 2026AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation
  8. 2026VD-DeepStack: Bridging Visual Comparison and Language Reasoning for Few-Shot Anomaly Detection