arXiv 2605.150242026-05-14cs.CV

HiSem：面向遥感图像变化描述的层次语义解缠

HiSem: Hierarchical Semantic Disentangling for Remote Sensing Image Change Captioning

College of Computer Science, Inner Mongolia University（内蒙古大学计算机学院）；Research Center for Spatiotemporal Intelligence, Inner Mongolia University（内蒙古大学时空智能研究中心）；Department of Aerospace Intelligent Science and Technology, School of Astronautics, Beihang University（北航宇航学院航空航天智能科学与技术系）；State Key Laboratory of Virtual Reality Technology and Systems, Beihang University（北航虚拟现实技术与系统国家重点实验室）；China Mobile Communications Group Inner Mongolia Co., Ltd.（中国移动通信集团内蒙古有限公司）

Man Wang, Chenyang Liu, Wenjun Li, Feng Ni, Bing Jia, Baoqi Huang, Riting Xia, Zhenwei Shi

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出HiSem网络，通过层次化语义解缠模块解决遥感图像变化描述中语义纠缠问题，提升变化检测的准确性和描述质量。

摘要：

遥感图像变化描述（RSICC）旨在实现双时相图像间真实变化的高层语义理解。尽管已有进展，现有方法受限于共享建模假设：变化与未变化图像对因内在语义粒度差异而被统一建模策略处理，导致粗粒度变化存在判断与细粒度语义理解之间的语义纠缠。为解决此限制，本文提出一种新颖的层次语义解缠网络（HiSem），明确解缠不同粒度的语义表示。具体而言，我们首先引入双向差分注意力调节（BDAM）模块，利用差异感知注意力增强跨时间交互，从而放大真实变化信号并抑制无关变化。在此基础上，我们设计了层次自适应语义解缠（HASD）模块，通过两个层次的自适应路由机制：粗粒度的图像级路由机制区分变化与未变化图像对，而细粒度的标记级混合专家（MoE）块对变化样本建模多样且异质的语义。在两个基准数据集上的广泛实验表明，HiSem在WHU-CDC数据集上实现了+7.52%的BLEU-4提升。更重要的是，本文方法通过显式对齐模型设计与双时相场景的内在语义异质性，为RSICC提供了结构化视角。代码将在https://github.com/Man-Wang-star/HiSem提供。

英文摘要：

Remote sensing image change captioning (RSICC) aims to achieve high-level semantic understanding of genuine changes occurring between bi-temporal images. Despite notable progress, existing methods are fundamentally limited by a shared modeling assumption: changed and unchanged image pairs, which have intrinsically different semantic granularities, are processed under a unified modeling strategy. This modeling inconsistency leads to semantic entanglement between coarse-grained change existence judgment and fine-grained semantic understanding.To address the above limitation, we propose a novel hierarchical semantic disentangling network (HiSem) that explicitly disentangles semantic representations of different granularities. Specifically, we first introduce the Bidirectional Differential Attention Modulation (BDAM) module that leverages discrepancy-aware attention to enhance cross-temporal interactions, thereby amplifying true change signals while suppressing irrelevant variations. Building upon this, we design a Hierarchical Adaptive Semantic Disentanglement (HASD) module that performs adaptive routing at two hierarchical levels: a coarse-grained image-level routing mechanism distinguishes changed and unchanged image pairs, while a fine-grained token-level Mixture-of-Experts (MoE) block models diverse and heterogeneous change semantics for changed samples. Extensive experiments on two benchmark datasets demonstrate that HiSem outperfoms previous methods, achieving a significant improvement of +7.52\% BLEU-4 on the WHU-CDC dataset. More importantly, our approach provides a structured perspective for RSICC by explicitly aligning model design with the intrinsic semantic heterogeneity of bi-temporal scenes. The code will be available at https://github.com/Man-Wang-star/HiSem

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。