从吸引到平衡：面向零样本异常检测的物理启发式语义引力子
From Attraction to Equilibrium: Physics-Inspired Semantic Gravitons for Zero-Shot Anomaly Detection
把 CLIP 的视觉-文本对齐建模为可学习的「语义引力子」中介，用交替耦合与能量势正则稳定跨模态对应，可直接迁移到需要精确定位的零样本/开放词表视觉任务（异常检测、缺陷分割、开放词表定位）。
原文依据 we propose the Semantic Graviton Network (SGNet), a physics-inspired framework that models multimodal alignment as an adaptive potential field
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论零样本异常检测（ZSAD）旨在无异常监督的情况下识别未见过的异常，这对开放世界场景至关重要。近期 CLIP 等视觉语言模型通过共享的视觉-文本嵌入实现异常推理，但现有方法往往依赖粗粒度的提示词融合，导致域偏移下对齐不稳定、定位不精确。为解决该问题，我们提出语义引力子网络（SGNet），一个将多模态对齐建模为自适应势场的物理启发式框架。我们引入语义引力子——可学习的动态中介，通过吸引与平衡力建立局部语义平衡，从而桥接视觉与文本模态。引力子交互网络交替进行文本到引力子与视觉到引力子的耦合，以逐步细化多模态对应关系，而基于能量的势正则化进一步稳定交互过程。在十个工业与医学基准上的大量实验表明，SGNet 在零样本异常检测上取得了最优性能。
英文原文摘要 1130 字符
Zero-shot anomaly detection (ZSAD) aims to identify unseen anomalies without abnormal supervision, which is essential for open-world scenarios. Recent vision-language models such as CLIP enable anomaly reasoning through shared visual-textual embeddings, but existing methods often rely on coarse prompt fusion, leading to unstable alignment and imprecise localization under domain shifts. To address this issue, we propose the Semantic Graviton Network (SGNet), a physics-inspired framework that models multimodal alignment as an adaptive potential field. We introduce semantic gravitons, learnable dynamic mediators that bridge visual and textual modalities by establishing localized semantic equilibria through attraction and equilibrium forces. A graviton interaction network alternates text-to-graviton and vision-to-graviton coupling to progressively refine multimodal correspondence, while an energy-based potential regularization further stabilizes the interaction process. Extensive experiments on ten industrial and medical benchmarks show that SGNet achieves state-of-the-art performance for zero-shot anomaly detection.