Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection

• URL: http://arxiv.org/abs/2607.03817v1
• Date: Sat, 04 Jul 2026 11:05:57 GMT
• Title: Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection
• Abstract summary: We present Global Logic and Local Search (GLLS), a training-free framework for reference-guided multimodal in-context verification.<n>GLLS uses a Part-Aware Visual-Logical Atlas to organize normal references and structured specifications in the inference context.<n> Experiments on MMAD-QA and additional anomaly detection datasets show consistent gains over matched and general-purpose baselines.
• Score: 27.04976556268606
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Multimodal Models (LMMs) show strong few-shot generalization, but industrial anomaly detection remains difficult because defects are small, input resolution is limited, and textual standards are not always grounded in visual evidence. Recent optimization-based methods improve alignment through fine-tuning, but they often require many defective samples, which are unavailable in early deployment. We present Global Logic and Local Search (GLLS), a training-free framework for reference-guided multimodal in-context verification. GLLS uses a Part-Aware Visual-Logical Atlas to organize normal references and structured specifications in the inference context. It combines a Global & Logic Stream, where SAM 3 extracts partially checkable visual facts, with a Fine-Grained & Actions Stream, where MCTS selects local evidence crops under a fixed budget. Experiments on MMAD-QA and additional anomaly detection datasets show consistent gains over matched and general-purpose baselines, while keeping the final diagnostic decision traceable to explicit visual evidence throughout the inspection trace.

Related papers

• UniSLAD: A Unified Framework for Structural and Logical Industrial Visual Anomaly Detection [4.587829504952397]
  We propose a unified framework, termed UniSLAD, which jointly addresses logical and structural anomalies without additional training.<n>First, we introduce a dual-feature extractor that synergistically integrates a Convolutional Neural Network (CNN) backbone for local texture perception with a Transformer backbone for global contextual reasoning.<n>At the patch level, memory banks enhanced by the Mahalanobis Transform (MT) preserve representative features and support more discriminative anomaly scoring.
  arXiv  Detail & Related papers  (2026-06-18T13:11:31Z)
• AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly Detection [43.187781277950386]
  We propose textbfAnomalyAgent, a training-free agentic framework for anomaly detection.<n>Key ingredients include textbf1) a comprehensive anomaly-centric toolset, and textbf2) a customized memory module.<n>Experiment results demonstrate that our AnomalyAgent achieves substantially better performance compared to training-free VLM-based AD and generic agentic methods.
  arXiv  Detail & Related papers  (2026-05-28T16:05:42Z)
• Multi-Level Contextual Token Relation Modeling for Machine-Generated Text Detection [105.1403233464793]
  Machine-generated texts (MGTs) pose risks such as disinformation and phishing, underscoring the need for reliable detection.<n> Metric-based methods, which extract statistically distinguishable features of MGTs, are often more practical than complex model-based methods.<n>We propose a multi-level contextual token relation modeling framework for MGT detection.
  arXiv  Detail & Related papers  (2026-05-15T15:55:58Z)
• Referring Multiple Regions with Large Multimodal Models via Contextual Latent Steering [51.54461480047943]
  We introduce Contextual Latent Steering (CSteer), a training-free approach for guiding general LMMs to refer multiple regions contextually.<n>CSteer starts with pre-computing contextual vectors that implicitly represent visual referring behaviors.<n> Experimental results indicate that general LMMs with CSteer outperform tailored referring LMMs in most cases.
  arXiv  Detail & Related papers  (2026-05-03T11:34:36Z)
• Text-Guided Multimodal Unified Industrial Anomaly Detection [71.95719669933312]
  We propose a unified multimodal industrial anomaly detection framework guided by text semantics.<n>The framework consists of two core modules: a Geometry-Aware Cross-Modal Mapper and an Object-Conditioned Textual Feature Adaptor.<n>Our method achieves state-of-the-art performance in classification and localization under unsupervised settings.
  arXiv  Detail & Related papers  (2026-04-24T13:21:22Z)
• Unified Unsupervised Anomaly Detection via Matching Cost Filtering [113.43366521994396]
  Unsupervised anomaly detection (UAD) aims to identify image- and pixel-level anomalies using only normal training data.<n>We present Unified Cost Filtering (UCF), a generic post-hoc refinement framework for refining anomaly cost volume of any UAD model.
  arXiv  Detail & Related papers  (2025-10-03T03:28:18Z)
• CompassVerifier: A Unified and Robust Verifier for LLMs Evaluation and Outcome Reward [50.97588334916863]
  We develop CompassVerifier, an accurate and robust lightweight verifier model for evaluation and outcome reward.<n>It demonstrates multi-domain competency spanning math, knowledge, and diverse reasoning tasks, with the capability to process various answer types.<n>We introduce VerifierBench benchmark comprising model outputs collected from multiple data sources, augmented through manual analysis of metaerror patterns to enhance CompassVerifier.
  arXiv  Detail & Related papers  (2025-08-05T17:55:24Z)
• VMAD: Visual-enhanced Multimodal Large Language Model for Zero-Shot Anomaly Detection [19.79027968793026]
  Zero-shot anomaly detection (ZSAD) recognizes and localizes anomalies in previously unseen objects. Existing ZSAD methods are limited by closed-world settings, struggling to unseen defects with predefined prompts. We propose a novel framework VMAD (Visual-enhanced MLLM Anomaly Detection) that enhances MLLM with visual-based IAD knowledge and fine-grained perception.
  arXiv  Detail & Related papers  (2024-09-30T09:51:29Z)
• A Comprehensive Library for Benchmarking Multi-class Visual Anomaly Detection [89.92916473403108]
  This paper proposes a comprehensive visual anomaly detection benchmark, ADer, which is a modular framework for new methods.<n>The benchmark includes multiple datasets from industrial and medical domains, implementing fifteen state-of-the-art methods and nine comprehensive metrics.<n>We objectively reveal the strengths and weaknesses of different methods and provide insights into the challenges and future directions of multi-class visual anomaly detection.
  arXiv  Detail & Related papers  (2024-06-05T13:40:07Z)
• Learning Global-Local Correspondence with Semantic Bottleneck for Logical Anomaly Detection [6.553276620691242]
  This paper presents a novel framework, named Global-Local Correspondence Framework (GLCF), for visual anomaly detection with logical constraints. Visual anomaly detection has become an active research area in various real-world applications, such as industrial anomaly detection and medical disease diagnosis.
  arXiv  Detail & Related papers  (2023-03-10T08:09:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.