无需微调，用专家模型提升多模态大模型的工业缺陷检测精度
EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models
- 通过阈值引导提示选择和置信度感知注意力增强，融合专家模型与冻结的大模型
- 在MVTec-AD和VisA数据集上分别达到94.4%和88.1%的检测准确率
- 保持大模型语义理解能力，适合希望零成本提升检测性能的工程应用
多模态大语言模型（MLLM）可为工业缺陷检测提供语义描述与推理能力，但在二分类准确率上仍不及专业检测器。现有方法依赖微调或训练桥接模块对齐专家输出与模型输入，限制了模型适配性。本文提出EAGLE，一种无需微调的框架，将专家检测器与冻结的MLLM结合。EAGLE包含阈值引导提示选择（TGPS），利用专家模型统计量估计决策阈值并选取文本与视觉提示；以及置信度感知注意力锐化（CAAS），在专家置信度低时引导MLLM关注视觉证据。实验表明，正确异常预测与对真实缺陷区域更强的关注相关，EAGLE持续强化此关联。在MVTec-AD和VisA数据集上，对五种MLLM骨干网络均无参数更新，检测准确率分别达94.4%和88.1%，性能媲美微调方法，同时大幅保留原始语义推理能力。
原文摘要 · Abstract (English)
Multimodal large language models (MLLMs) can enrich industrial anomaly detection with semantic descriptions and anomaly reasoning, but they still lag specialist anomaly detectors in binary detection accuracy. Existing approaches address this gap by fine-tuning MLLMs or training bridging modules to align expert outputs with MLLM inputs, limiting flexibility across backbones. We propose EAGLE, a tuning-free framework that integrates expert anomaly detectors with frozen MLLMs. EAGLE consists of Threshold-Guided Prompt Selection (TGPS), which estimates a decision threshold from expert model statistics and selects textual and visual prompts, and Confidence-Aware Attention Sharpening (CAAS), which shifts MLLM attention toward visual evidence when expert confidence is low. Beyond improving accuracy, we analyze MLLM attention and find that correct anomaly predictions are associated with stronger focus on ground-truth defect regions; EAGLE consistently strengthens this alignment. On MVTec-AD and VisA, EAGLE improves five MLLM backbones without parameter updates, reaching up to 94.4\% and 88.1\% in anomaly discrimination accuracy, respectively, and achieving performance competitive with fine-tuning-based methods while largely preserving MLLM semantic reasoning ability.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。