发表机构
Neurogica Inc.（Neurogica公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出PoE-Fuse参数高效框架，通过精度加权融合冻结专家，以共享主干同时解决双时相变化检测、定位与损毁评估，平均F1达59.2%，优于指令调优助手和专用模型。
AI 中文摘要
双时相变化理解旨在定位并刻画两幅卫星图像之间发生的变化，是灾害响应和环境监测的核心任务，涵盖变化检测、建筑物定位和损毁评估。强大的视觉-语言模型能够处理这些任务，但对其进行适配通常需要全量微调或强化学习，成本高昂且不稳定。我们提出PoE-Fuse，一种参数高效的框架，它组合冻结的几何、定位和语言基础专家，将其特征重采样到共享的空间网格上，仅训练一个轻量级融合主干。PoE-Fuse将对齐后的特征视为潜在场景状态的高斯观测，并通过学习得到的逐单元精度进行融合。该专家乘积估计器严格推广了均匀求和与标量门控，并通过组合两个时间戳的精度扩展到变化场。一个共享主干同时解决三个任务，平均F1达到59.2%，而指令调优的时间视觉-语言助手仅为40.7%，并超越了在同一协议和训练预算下重新训练的专用变化检测模型。
英文摘要
Bi-temporal change understanding, which localizes and characterizes what changed between two satellite images, is central to disaster response and environmental monitoring, spanning change detection, building localization, and damage assessment. Strong vision-language models address these tasks, but adapting them typically requires full fine-tuning or reinforcement learning, which is costly and unstable. We propose PoE-Fuse, a parameter-efficient framework that instead composes frozen foundation experts for geometry, grounding, and language, resampling their features onto a shared spatial grid and training only a lightweight fusion trunk. PoE-Fuse treats the aligned features as Gaussian observations of a latent scene state and fuses them by learned per-cell precision. This product-of-experts estimator strictly generalizes uniform summation and scalar gating, and extends to change fields by composing the precisions of the two timestamps. A single shared trunk solves the three tasks at once, reaching a mean F1 of 59.2%, compared with 40.7% for an instruction-tuned temporal vision-language assistant, and surpassing dedicated change-detection models retrained under the same protocol and training budget.
CommentsAccepted by ACCV 2026
