UniGeoSeg：面向地理空间场景的统一开放世界分割
UniGeoSeg: Towards Unified Open-World Segmentation for Geospatial Scenes
该工作构建了百万级遥感指令驱动分割数据集与统一框架，其任务感知文本增强、潜变量知识记忆与渐进式训练策略可直接迁移到开放世界分割与指代/推理分割任务中，为视觉研究者提供可复用的多任务分割基线与评测基准。
原文依据 we present UniGeoSeg, a unified framework that serves as a strong baseline, incorporating task-aware text enhancement, latent knowledge memory, and a progressive training strategy
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论遥感领域中由指令驱动的分割能够根据引导信息生成掩码，为易用且可泛化的应用提供了巨大潜力。然而，现有方法存在任务表述碎片化和指令数据有限的问题，阻碍了有效的理解与泛化。为解决这些问题，我们提出了 GeoSeg-1M，这是首个面向遥感指令驱动分割的百万级数据集，通过自动掩码过滤与指令生成流程构建，从多个公开数据集中合成指代、交互和推理分割指令。GeoSeg-1M 包含 59 万张图像、117 个类别和 110 万个图像-掩码-指令三元组。在此基础上，我们进一步构建了 GeoSeg-Bench，这是一个具有挑战性的基准，旨在评估跨多种指令驱动任务和复杂地理空间场景的上下文理解与推理能力。此外，我们提出了 UniGeoSeg，一个作为强基线的统一框架，融合了任务感知文本增强、潜变量知识记忆和渐进式训练策略，以促进多任务学习。大量实验表明，UniGeoSeg 在 GeoSeg-Bench 和多种公开基准上取得了最优性能，并展现出强大的零样本泛化能力。数据集和源代码将公开发布。
英文原文摘要 1414 字符
Instruction-driven segmentation in remote sensing generates masks from guidance, offering great potential for accessible and generalizable applications. However, existing methods suffer from fragmented task formulations and limited instruction data, hindering effective understanding and generalization. To address these issues, we introduce GeoSeg-1M, the first million-scale dataset for remote sensing instruction-driven segmentation, constructed via an automatic mask filtering and instruction generation pipeline that synthesizes referring, interactive, and reasoning segmentation instructions from multiple public datasets. GeoSeg-1M contains 590K images, 117 categories, and 1.1M image-mask-instruction triplets. Building upon this foundation, we further curate GeoSeg-Bench, a challenging benchmark designed to evaluate contextual understanding and reasoning capabilities across diverse instruction-driven tasks and complex geospatial scenes. Furthermore, we present UniGeoSeg, a unified framework that serves as a strong baseline, incorporating task-aware text enhancement, latent knowledge memory, and a progressive training strategy to facilitate multi-task learning. Extensive experiments demonstrate the state-of-the-art performance of UniGeoSeg across GeoSeg-Bench and diverse public benchmarks, while exhibiting strong zero-shot generalization. The datasets and source code will be publicly released.