用YOLO检测器加速SAM，实现快速高精度图像分割。
Tiny-YOLOSAM: Fast Hybrid Image Segmentation
- 用YOLOv12生成框提示，仅对显著目标用稀疏点提示补全。
- 覆盖率达77.1%（原16.4%），平均交并比67.8%（原19.2%）。
- 推理时间缩短至10.39秒/图（原49.20秒），适合实时场景。
段一切模型（SAM）可实现高质量、可提示的分割，但在延迟敏感场景中计算开销过大。TinySAM是轻量化的蒸馏版SAM，保持了优秀的零样本掩码质量，但其“分割所有”模式仍需数百个提示，实际运行缓慢。我们首先在COCO val2017上复现TinySAM，使用官方检查点，结果与报告的AP相差不超过0.03%，建立了可靠的实验基线。在此基础上，提出Tiny-YOLOSAM，一种快速混合分割管道：利用近期的YOLOv12检测器为显著前景物体生成框提示，并仅在YOLO引导的掩码未覆盖区域采样稀疏点提示进行补充。在COCO val2017上，该混合系统显著提升无类别覆盖度（AR从16.4%提升至77.1%，mIoU从19.2%提升至67.8%），同时将端到端运行时间从49.20秒/图降至10.39秒/图（提速4.7倍），在Apple M1 Pro CPU上完成。
原文摘要 · Abstract (English)
The Segment Anything Model (SAM) enables promptable, high-quality segmentation but is often too computationally expensive for latency-critical settings. TinySAM is a lightweight, distilled SAM variant that preserves strong zero-shot mask quality, yet its "segment-everything" mode still requires hundreds of prompts and remains slow in practice. We first replicate TinySAM on COCO val2017 using official checkpoints, matching the reported AP within 0.03%, establishing a reliable experimental baseline. Building on this, we propose Tiny-YOLOSAM, a fast hybrid pipeline that uses a recent YOLO detector (YOLOv12) to generate box prompts for TinySAM on salient foreground objects, and supplements uncovered regions with sparse point prompts sampled only where YOLO-guided masks provide no coverage. On COCO val2017, the hybrid system substantially improves class-agnostic coverage (AR from 16.4% to 77.1%, mIoU from 19.2% to 67.8%) while reducing end-to-end runtime from 49.20s/image to 10.39s/image (4.7x) on an Apple M1 Pro CPU. These results suggest detector-guided prompting combined with targeted sparse sampling as an effective alternative to dense "segment-everything" prompting for practical full-scene 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。