STAND：语义锚定约束与双粒度消歧用于遥感图像变化描述
STAND: Semantic Anchoring Constraint with Dual-Granularity Disambiguation for Remote Sensing Image Change Captioning
AI总结：
STAND通过语义锚定约束与双粒度消歧方法，解决遥感图像变化描述中的视角、尺度和先验知识模糊问题，提升描述精度。
摘要：
遥感图像变化描述（RSICC）旨在描述两幅遥感图像之间的差异。尽管近期方法探索了视频建模，但大多忽视了视角、尺度和先验知识的内在模糊性，缺乏对编码器的有效约束。本文提出STAND，一种用于RSICC的语义锚定约束与双粒度消歧方法，逐步解决这些模糊性。具体而言，为建立可靠的特征基础，我们首先引入可解释的约束来正则化时间表示。在这些净化的特征上，双粒度消歧模块通过耦合宏观级全局上下文聚合以解决视角混淆，与微观级频率聚焦注意力以增强小物体尺度，解决空间不确定性。最终，为将这些视觉消歧特征转化为精确文本，语义概念锚定模块利用语言类别先验知识，在解码过程中解决知识模糊性。大量实验验证了STAND的优越性和其在解决模糊性方面的有效性。
英文摘要：
Remote sensing image change captioning (RSICC) aims to describe the difference between two remote sensing images. While recent methods have explored video modeling, they largely overlook the inherent ambiguities in viewpoint, scale, and prior knowledge, lacking effective constraints on the encoder. In this paper, we present STAND, a Semantic Anchoring Constraint with Dual-Granularity Disambiguation for RSICC, to progressively resolve these ambiguities. Specifically, to establish a reliable feature foundation, we first introduce an interpretable constraint to regularize temporal representations. Operating on these purified features, a dual-granularity disambiguation module resolves spatial uncertainties by coupling macro-level global context aggregation for viewpoint confusion with micro-level frequency-refocused attention for small-object scale enhancement. Ultimately, to translate these visually disambiguated features into precise text, a semantic concept anchoring module leverages language categorical priors to tackle knowledge ambiguity during decoding. Extensive experiments verify the superiority of STAND and its effectiveness in addressing ambiguities.
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。
