不训练即可实现遥感图像开放词汇分割，通过上下文感知提升分割一致性。
ConInfer: Context-Aware Inference for Training-Free Open-Vocabulary Remote Sensing Segmentation
- 基于视觉语言模型，联合多个空间单元进行语义推理，显式建模区域间依赖关系。
- 在开放词汇分割和目标提取任务上分别提升2.80%和6.13%准确率。
- 适合需要快速适配新类别、无标注数据的遥感场景应用。
无需训练的开放词汇遥感分割（OVRSS）借助视觉语言模型，成为实现遥感图像类别无关语义理解的新兴范式。现有方法主要聚焦于增强特征表示或缓解模态差异以提升像素级预测精度，但独立的逐块预测方式与遥感数据固有的大尺度、强空间与语义相关性特征不匹配。为此，我们提出ConInfer——一种面向OVRSS的上下文感知推理框架，通过联合多个空间单元并显式建模其内部语义依赖关系，引入全局上下文信息，显著提升复杂遥感环境下的分割一致性、鲁棒性与泛化能力。在多个基准数据集上的大量实验表明，本方法持续优于现有基于视觉语言模型的单像素基线（如SegEarth-OV），在开放词汇语义分割和目标提取任务上分别取得2.80%和6.13%的平均提升。代码已公开：https://github.com/Dog-Yang/ConInfer。
原文摘要 · Abstract (English)
Training-free open-vocabulary remote sensing segmentation (OVRSS), empowered by vision-language models, has emerged as a promising paradigm for achieving category-agnostic semantic understanding in remote sensing imagery. Existing approaches mainly focus on enhancing feature representations or mitigating modality discrepancies to improve patch-level prediction accuracy. However, such independent prediction schemes are fundamentally misaligned with the intrinsic characteristics of remote sensing data. In real-world applications, remote sensing scenes are typically large-scale and exhibit strong spatial as well as semantic correlations, making isolated patch-wise predictions insufficient for accurate segmentation. To address this limitation, we propose ConInfer, a context-aware inference framework for OVRSS that performs joint prediction across multiple spatial units while explicitly modeling their inter-unit semantic dependencies. By incorporating global contextual cues, our method significantly enhances segmentation consistency, robustness, and generalization in complex remote sensing environments. Extensive experiments on multiple benchmark datasets demonstrate that our approach consistently surpasses state-of-the-art per-pixel VLM-based baselines such as SegEarth-OV, achieving average improvements of 2.80% and 6.13% on open-vocabulary semantic segmentation and object extraction tasks, respectively. The implementation code is available at: https://github.com/Dog-Yang/ConInfer
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。