让SAM模型学会自适应红外小目标分割的提示与响应。
SPARK-SAM: Learning How to Prompt and Respond for Infrared Small Target Segmentation
- 通过联合自提示状态引导解码器，学习目标域响应知识。
- 在三个数据集上最高达86.49%的分割准确率，优于14种变体。
- 适合做红外图像小目标自动分割的研究者和工程师。
可提示分割模型提供可复用接口，但直接迁移到红外小目标分割（IRSTD）时，空间提示与目标域掩码响应之间存在不匹配。在使用从测试参考掩码确定性生成的松散框提示进行诊断时，最佳官方SAM2.1结果在NUAA-SIRST、NUDT-SIRST和IRSTD-1K上的交并比（IoU）分别为4.69%、1.64%和2.28%。我们提出SPARK-SAM（基于响应知识的自提示适配），通过图像条件下的联合自提示状态学习目标域响应知识并引导解码器。训练结合基准掩码监督与可靠性感知响应引导。SPARK-SAM以0.726M额外参数实现75.78%、86.49%和68.34%的IoU，成为14种重训练SAM变体中两个基准的第一名。阶段式IRSTD-1K诊断显示，响应适配在预测点获得可靠目标定位前已达到大部分最终性能。提示监督使预测提示候选与目标位置对齐，冻结权重干预测量输出对联合自提示状态的敏感性。匹配消融实验表明，响应引导与高分辨率提示精炼在所有三个数据集上均带来稳定增益。代码已开源：https://github.com/Sakauma/SPARK-SAM。
原文摘要 · Abstract (English)
Promptable segmentation models provide a reusable interface, but direct transfer to automatic infrared small-target segmentation (IRSTD) exposes a mismatch between spatial prompts and target-domain mask responses. In a diagnostic using target-covering loose-box prompts deterministically derived from test reference masks, the best official SAM2.1 results are only 4.69%, 1.64%, and 2.28% IoU on NUAA-SIRST, NUDT-SIRST, and IRSTD-1K. We introduce SPARK-SAM (Self-Prompt Adaptation with Response Knowledge for SAM), which learns target-domain response knowledge and conditions the decoder through an image-conditioned joint self-prompt state. Training combines benchmark-mask supervision with reliability-aware response guidance. SPARK-SAM achieves 75.78%, 86.49%, and 68.34% IoU with 0.726M additional parameters, ranking first on two benchmarks among 14 retrained SAM variants and adaptations evaluated as automatic image-to-mask methods. The staged IRSTD-1K diagnostic shows that response adaptation reaches most of the final IoU before the predicted points acquire reliable target grounding. Prompt supervision aligns the predicted prompt candidates with target locations, and frozen-weight interventions measure output sensitivity to the joint self-prompt state. Matched ablations show consistent accuracy gains from response guidance and high-resolution prompt refinement across all three datasets. Code is available at https://github.com/Sakauma/SPARK-SAM.
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。