English

Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentation

Computer Vision and Pattern Recognition 2025-11-25 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2511.19062,
  title  = {Granular Computing-driven SAM: From Coarse-to-Fine Guidance for Prompt-Free Segmentation},
  author = {Qiyang Yu and Yu Fang and Tianrui Li and Xuemei Cao and Yan Chen and Jianghao Li and Fan Min and Yi Zhang},
  journal= {arXiv preprint arXiv:2511.19062},
  year   = {2025}
}

Comments

19 pages, 7 figures

R2 v1 2026-07-01T07:52:03.568Z