无需训练，用流场优化实现遥感图像实体级少样本分割
Training-Free Entity-Level Few-Shot Segmentation of Remote Sensing Images with Advection Refinement
- 将像素预测转为实体推理，构建多模态语义场
- 引入流体力学式精修机制，提升语义连续性并去噪
- 完全免训练，适合快速适配新遥感场景
现有跨域少样本分割方法因源域周期性训练和像素级密集预测导致高训练成本，且常产生碎片化与噪声预测。为此，我们提出一种无需训练的遥感图像实体级少样本分割框架，结合对流精修机制。首先利用SAM3的通用几何先验生成类别无关的实体初元；通过将少样本推理重构为实体级推理，融合前景/背景原型与SAM3的密集文本语义响应，构建多模态语义势场。进一步引入基于对流方程的语义精修机制，在特征空间与相似性空间中传播类别感知信息，增强语义连续性并抑制局部纹理噪声。在多个遥感数据集上的实验表明，该框架有效缓解领域偏移与局部噪声，显著提升SAM3在遥感少样本分割中的适应能力，且无需额外训练。代码将公开于 https://github.com/yu-ni1989/ELFSS-AR。
原文摘要 · Abstract (English)
Existing cross-domain few-shot segmentation approaches suffer from high training costs due to source-domain episodic training and pixel-wise dense prediction, while often producing fragmented and noisy predictions. To overcome these issues, we propose a training-free entity-level few-shot segmentation framework for remote sensing images with advection refinement. Specifically, we first leverage SAM3's generic geometric priors to generate category-agnostic entity primitives. By reformulating few-shot inference from pixel-level prediction to entity-level reasoning, foreground and background prototypes are constructed and combined with dense textual semantic responses from SAM3 to build a multi-modal semantic potential field. Furthermore, an advection equation-based semantic refinement mechanism is introduced to propagate category-aware information across both feature and similarity spaces, enhancing semantic continuity and suppressing local texture noise. Extensive experiments on multiple remote sensing datasets demonstrate that the proposed framework effectively mitigates domain shift and local noise, substantially improving SAM3's adaptation capability for remote sensing few-shot segmentation without additional training. Our code will be publicly available at https://github.com/yu-ni1989/ELFSS-AR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。