{"ID":5551607,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-04T14:57:24.495699864Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01049","arxiv_id":"2607.01049","title":"GenAU: Language-Grounded Industrial Anomaly Understanding with Vision-Language Models","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.","short_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-...","url_abs":"https://arxiv.org/abs/2607.01049","url_pdf":"https://arxiv.org/pdf/2607.01049v1","authors":"[\"Hongkuan Zhou\",\"Tristan Rehm\",\"Nadeem Nazer\",\"Lavdim Halilaj\",\"Jingcheng Wu\",\"Steffen Staab\"]","published":"2026-07-01T15:11:29Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Language Model\"]","has_code":false}