IAD-Unify：一种基于区域的统一模型用于工业异常分割、理解和生成
IAD-Unify: Task-Specific Interfaces for Industrial Anomaly Understanding, Segmentation, and Generation
AI总结：
本文提出IAD-Unify模型，通过双重编码框架实现工业异常的分割、理解和生成，构建了统一的评估平台，并展示了其在跨类别泛化上的强大性能。
摘要：
现实中的工业检测不仅需要定位缺陷，还需要用自然语言解释缺陷并生成受控的缺陷编辑。然而，现有方法未能在一个统一框架和评估协议中共同支持这三项能力。我们提出了IAD-Unify，一种双编码统一框架，其中冻结的DINOv2基于区域专家通过轻量级令牌注入为共享的Qwen3.5-4B视觉-语言主干提供精确的异常证据，共同实现异常分割、基于区域的理解和掩码引导的生成。为了实现统一评估，我们进一步构建了Anomaly-56K，一个全面的统一多任务IAD评估平台，涵盖59,916张图像，跨越24个类别和104种缺陷变体。受控消融实验得出四个发现：（i）区域定位是理解的关键机制，移除它会降低定位精度76pp以上；（ii）预测区域性能与 oracle 接近，证实了部署可行性；（iii）基于区域的生成在全图像保真度和掩码区域感知质量方面表现最佳；（iv）预初始化的联合训练在不增加生成成本的情况下提高了理解能力（-0.16 dB）。IAD-Unify在MMAD基准测试中也表现出色，包括训练期间未见过的类别，展示了强大的跨类别泛化能力。
英文摘要：
Industrial anomaly inspection requires complementary capabilities: explaining an observed defect, localizing its pixels, and synthesizing a controlled edit. We present IAD-Unify, a unified architecture connecting a multimodal language model (MLLM), dense visual expert, and diffusion editor through task-specific token interfaces. A multi-reference DINOv2 pathway forms a dense anomaly field and compresses its 1,369 cells into 81 structured evidence tokens. Qwen3.5 consumes these tokens for grounded answers and, with 32 task tokens, converts them into a semantic residual over the dense mask. A separate 256-query interface resamples Qwen states into Stable Diffusion's complete cross-attention context, while the editor retains its source latent and hard-mask inputs. The task pathways share one Qwen adaptation without forcing every task through the same visual bottleneck; in particular, evidence tokens are excluded from the generation pathway. Staged optimization initializes dense evidence, aligns it with language, calibrates segmentation, and then pretrains and specializes the diffusion editor while preserving earlier capabilities. We also construct Anomaly Evidence over 54,501 deduplicated industrial images. Its quality-controlled Anomaly Evidence Compiler and Industrial Edit-Pair Compiler produce family-disjoint, validated supervision through independent geometry, semantic-grounding, and edit-consistency checks. This design provides one fixed shared parameter set for understanding, segmentation, and localized generation without conflating their inputs, supervision, or outputs. The resulting model reaches 73.02% MMAD Macro$_7$, the highest listed public segmentation AP average (57.10%) with one reference, and the lowest Controlled masked DINO distance (0.3765), with complementary strengths across reasoning, pixel ranking, and semantic edit fidelity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
