GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models

• URL: http://arxiv.org/abs/2607.01049v1
• Date: Wed, 01 Jul 2026 15:11:29 GMT
• Title: GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models
• Abstract summary: GenAU is a vision-language framework for industrial Anomaly Understanding.<n>It unifies image-level detection, pixel-level segmentation, multi-type anomaly detection, and defect analysis in a single instruction-following model.<n>It attains the strongest image-level detection among CLIP-based zero-shot methods on VisA and Real-IAD.
• Score: 12.502139331711673
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Industrial inspection requires more than binary anomaly detection: a practical system should determine whether an anomaly exists, localize the defective region, identify the defect type, and provide interpretable visual evidence. Existing CLIP-based methods detect and localize anomalies well but offer limited language-level defect understanding, while instruction-tuned vision-language models can describe defects but do not natively produce pixel-level masks. We introduce GenAU, a Generalist vision-language framework for industrial Anomaly Understanding that unifies image-level detection, pixel-level segmentation, multi-type anomaly detection, and defect analysis in a single instruction-following model. GenAU augments a vision-language model with two segmentation tokens, [SEG_defect] and [SEG_normal], whose hidden states act as language-grounded queries over multi-scale visual features for pixel-level localization; the image-level score fuses this map with the decoder's textual normal/defect decision, while the language decoder produces structured defect-aware responses. Trained with a joint language-modeling and segmentation objective, GenAU covers all four tasks within one architecture and recipe, adding zero-shot multi-type detection and language-grounded defect analysis at a quantified cost to detection and segmentation. Across cross-dataset benchmarks, GenAU attains the strongest image-level detection among CLIP-based zero-shot methods on VisA and Real-IAD, with segmentation approaching but not surpassing specialized CLIP baselines.

Related papers

• Beyond Static Anchors: Bounded Prototype Conditioning for Language-Free Medical Anomaly Detection [52.986874008247554]
  We propose ReCAP, a language-free framework that replaces static anchors with input-conditioned visual prototypes.<n>ReCAP re-centers separated normal and abnormal prototypes for each image through a bounded gated modulation.<n>It achieves the best image-level AUROC on all zero-shot and 23 of 24 few-shot settings, and the best zero-shot pixel-level AUROC on all three segmentation datasets.
  arXiv  Detail & Related papers  (2026-08-01T04:46:55Z)
• OPD-IAD: From Language Judgment to Industrial Anomaly Detection via On-Policy Self-Distillation [42.193887957394345]
  Large vision-language models (LVLMs) have recently shown strong potential for industrial anomaly detection (IAD)<n>We propose textbfOPD-IAD, an evidence-privileged dense on-policy self-distillation framework for LVLM-based IAD.<n> OPD-IAD distills privileged defect evidence onto the model's own on-policy judgment trajectory, enabling the final generated judgment to be learned under dense supervision.
  arXiv  Detail & Related papers  (2026-07-21T08:37:01Z)
• Leveraging Hierarchical Image-Text Misalignment for Universal Fake Image Detection [58.927873049646024]
  We show that fake images cannot be properly aligned with corresponding captions compared to real images.<n>We propose a simple yet effective ITEM by leveraging the image-text misalignment in a joint visual-language space as discriminative clues.
  arXiv  Detail & Related papers  (2025-11-01T06:51:14Z)
• Towards Fine-Grained Vision-Language Alignment for Few-Shot Anomaly Detection [65.29550320117526]
  We propose a novel framework named FineGrainedAD to improve anomaly localization performance.<n> Experiments demonstrate that the proposed FineGrainedAD achieves superior overall performance in few-shot settings.
  arXiv  Detail & Related papers  (2025-10-30T13:09:00Z)
• IAD-GPT: Advancing Visual Knowledge in Multimodal Large Language Model for Industrial Anomaly Detection [70.02774285130238]
  This paper explores the combination of rich text semantics with both image-level and pixel-level information from images.<n>We propose IAD-GPT, a novel paradigm based on MLLMs for Industrial Anomaly Detection.<n>Experiments on MVTec-AD and VisA datasets demonstrate our state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-10-16T02:48:05Z)
• InspectVLM: Unified in Theory, Unreliable in Practice [0.0]
  Unified vision-language models (VLMs) promise to streamline computer vision pipelines by reframing multiple visual tasks within a single language-driven interface.<n>We critically evaluate the viability of this unified paradigm using InspectVLM, a Florence-2-based VLM trained on InspectMM.
  arXiv  Detail & Related papers  (2025-08-03T21:09:35Z)
• OoDDINO:A Multi-level Framework for Anomaly Segmentation on Complex Road Scenes [3.0743391441996684]
  Anomaly segmentation aims to identify Out-of-Distribution (OoD) anomalous objects within images.<n>Existing pixel-wise methods typically assign anomaly scores individually and employ a global thresholding strategy to segment anomalies.<n>We introduce OoDDINO, a novel multi-level anomaly segmentation framework designed to address these limitations.
  arXiv  Detail & Related papers  (2025-07-02T08:15:11Z)
• MultiADS: Defect-aware Supervision for Multi-type Anomaly Detection and Segmentation in Zero-Shot Learning [27.235318937019255]
  It is crucial to know the distinct type of defect, such as a bent, cut, or scratch.<n>The ability to recognize the "exact" defect type enables automated treatments of the anomalies in modern production lines.<n>We propose MultiADS, a zero-shot learning approach, able to perform Multi-type Anomaly Detection.
  arXiv  Detail & Related papers  (2025-04-09T09:52:04Z)
• FADE: Few-shot/zero-shot Anomaly Detection Engine using Large Vision-Language Model [0.9226774742769024]
  Few-shot/zero-shot anomaly detection is important for quality inspection in the manufacturing industry. We propose the Few-shot/zero-shot Anomaly Engine Detection (FADE) which leverages the vision-language CLIP model and adjusts it for the purpose of anomaly detection. FADE outperforms other state-of-the-art methods in anomaly segmentation with pixel-AUROC of 89.6% (91.5%) in zero-shot and 95.4% (97.5%) in 1-normal-shot.
  arXiv  Detail & Related papers  (2024-08-31T23:05:56Z)
• Bootstrap Fine-Grained Vision-Language Alignment for Unified Zero-Shot Anomaly Localization [63.61093388441298]
  Contrastive Language-Image Pre-training models have shown promising performance on zero-shot visual recognition tasks. In this work, we propose AnoCLIP for zero-shot anomaly localization.
  arXiv  Detail & Related papers  (2023-08-30T10:35:36Z)
• Reference-based Defect Detection Network [57.89399576743665]
  The first issue is the texture shift which means a trained defect detector model will be easily affected by unseen texture. The second issue is partial visual confusion which indicates that a partial defect box is visually similar with a complete box. We propose a Reference-based Defect Detection Network (RDDN) to tackle these two problems.
  arXiv  Detail & Related papers  (2021-08-10T05:44:23Z)

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.