CDICS：通过组合式提示与分阶段解耦探索上下文分割中的细粒度属性
CDICS: Delving Into Fine-Grained Attribute for In-Context Segmentation via Compositional Prompts and Phased Decoupling
提出组合式提示（语义、部件、颜色图像）控制上下文分割，并采用两阶段解耦架构先粗定位后细粒度属性匹配，为细粒度可控分割提供了可复用的提示设计与训练策略。
原文依据 we propose CDICS, a novel framework that leverages Compositional prompts and phased task Decoupling to achieve compositional prompt-controlled In-Context Segmentation.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论上下文学习（ICL）在发展通用图像分割模型方面已展现出显著有效性。其相较于文本描述的重要优势在于能够通过简单的参考图像传达复杂的视觉外观细节。然而，针对现实世界中罕见且复杂的概念，找到完美匹配的单一示例十分困难。此外，现有方法在很大程度上局限于对参考图像的语义或实例级理解，难以通过输入表达更精确的分割需求。为解决这一问题，我们提出CDICS，一种新颖的框架，利用组合式提示与分阶段任务解耦来实现组合式提示控制的上下文分割。我们的方法引入源自参考提示的组合式提示，结合语义、部件和颜色图像来动态定义分割目标。为有效融合这些控制信息、确保协同同时抑制干扰并降低特征耦合风险，我们的解耦两阶段架构首先执行粗粒度语义定位，然后利用组合式外观提示对结果进行细化，以精确匹配指定的属性。这一设计扩展了传统的上下文分割，使其能够支持组合式提示。此外，我们重建了两个数据集及其基准，以获取具有部件-颜色特定属性的数据。我们的方法在组合式提示控制的上下文分割任务上展现出优越性能。它还扩展了现有上下文分割的能力，并向现实世界的细粒度分割迈出了尝试性的一步。
英文原文摘要 1701 字符
In-Context Learning (ICL) has shown great effectiveness in developing generalist image segmentation models. Its significant advantage over text-based descriptions is the ability to convey intricate visual appearance details through simple reference images. However, finding a perfectly matching single example for real-world rare and complex concepts is difficult. Moreover, existing methods are largely confined to semantic or instance-level understanding of the reference image, struggling to express more precise segmentation needs through the input. To address this, we propose CDICS, a novel framework that leverages Compositional prompts and phased task Decoupling to achieve compositional prompt-controlled In-Context Segmentation. Our method introduces compositional prompts derived from reference prompts, combining semantic, part and color images to dynamically define segmentation targets. To effectively fuse this control information, ensure synergy while suppressing interference, and mitigate feature coupling risks, our decoupled two-stage architecture firstly performs coarse-grained semantic localization, then refines the result using compositional appearance prompts to precisely match the specified attributes. This design extends traditional in-context segmentation, enabling it to support compositional prompts. Additionally, we reconstructed two datasets and their benchmarks to acquire data with part-color-specific attributes. Our method demonstrates superior performance on the compositional prompt-controlled in-context segmentation task. It also extends the capabilities of existing in-context segmentation, and makes an attempt toward real-world fine-grained segmentation.