无需手动提示，自动分区域精准分割图像。
Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentation
- 分阶段处理：先粗后细，自适应定位显著区域
- 高分辨率下分割精度提升，支持细粒度建模
- 用生成的掩码替代人工提示，适合自动化场景
免提示图像分割旨在不依赖人工引导的情况下生成准确掩码。现有预训练模型（如分割一切模型SAM）通常在单一粒度级别生成提示，存在两个局限：(1) 局部定位能力弱，缺乏自主区域定位机制；(2) 可扩展性差，难以在高分辨率下实现精细建模。为此，我们提出基于粒计算（GrC）的粗到细框架Grc-SAM。首先，在粗粒度阶段自适应提取特征中高响应区域，实现精确前景定位并减少对外部提示的依赖；其次，在细粒度阶段采用更细粒度的块划分与稀疏局部Swin风格注意力，增强细节建模能力，支持高分辨率分割；第三，将优化后的掩码编码为潜在提示嵌入，输入SAM解码器，以自动化推理过程替代手工提示。通过融合多粒度注意力机制，Grc-SAM实现了粒计算与视觉变换器的结合。大量实验表明，Grc-SAM在准确性和可扩展性上均优于基线方法，为免提示分割提供了独特的粒计算视角。
原文摘要 · Abstract (English)
Prompt-free image segmentation aims to generate accurate masks without manual guidance. Typical pre-trained models, notably Segmentation Anything Model (SAM), generate prompts directly at a single granularity level. However, this approach has two limitations: (1) Localizability, lacking mechanisms for autonomous region localization; (2) Scalability, limited fine-grained modeling at high resolution. To address these challenges, we introduce Granular Computing-driven SAM (Grc-SAM), a coarse-to-fine framework motivated by Granular Computing (GrC). First, the coarse stage adaptively extracts high-response regions from features to achieve precise foreground localization and reduce reliance on external prompts. Second, the fine stage applies finer patch partitioning with sparse local swin-style attention to enhance detail modeling and enable high-resolution segmentation. Third, refined masks are encoded as latent prompt embeddings for the SAM decoder, replacing handcrafted prompts with an automated reasoning process. By integrating multi-granularity attention, Grc-SAM bridges granular computing with vision transformers. Extensive experimental results demonstrate Grc-SAM outperforms baseline methods in both accuracy and scalability. It offers a unique granular computational perspective for prompt-free segmentation.
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。