发表机构
The Center for Advanced Computer Studies (CACS), School of Computing and Informatics, University of Louisiana at Lafayette; Department of Computer Science, LSU New Orleans; US Army Corps of Engineers, Engineer Research and Development Center（路易斯安那大学拉斐特分校计算与信息学院高级计算机研究中心; 路易斯安那州立大学新奥尔良分校计算机科学系; 美国陆军工程兵团工程师研究与发展中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对土堤管涌分割中标注示例稀缺问题，提出无泄漏交叉验证堆叠框架，通过五折交叉验证训练模型并校准，结合逐像素元学习器，改进后的模型在测试集上交并比提升，还引入新合成路线，降低标注成本。
AI 中文摘要
管涌是土堤内部侵蚀的早期预警信号，深层分割网络越来越多地用于在检查照片中发现它们。但标注示例稀缺，常见方法会悄悄提高报告的准确率。本文提出一个管涌分割框架，封闭了这些漏洞。每个合成图像都指向其真实父图像，通过五折交叉验证训练五个编码器 - 解码器主干，每个主干由一个温度标量校准，由仅在折外预测上拟合的逐像素元学习器组合。在保留测试集上，改进后的SandBoilNet在三个种子上的交并比达到0.707，校准堆叠达到0.681。还引入了掩码条件合成路线，以零标注成本生成带标注的训练图像。
英文摘要
Sand boils, points where water seeping beneath an earthen levee re-emerges at the surface, are early warnings of internal erosion, and deep segmentation networks are increasingly used to find them in inspection photographs. Annotated examples are scarce, and two common ways of working around that scarcity quietly inflate reported accuracy: tuning ensemble weights on the same images later used to score them, and training on synthetic images derived from the very photographs held out for testing. We present a sand-boil segmentation framework that closes both loopholes. Every synthetic image carries a pointer to its real parent, and a per-fold filter excludes any image whose parent is held out; five encoder-decoder backbones are trained under five-fold cross-validation, calibrated by one temperature scalar each, and combined by a per-pixel meta-learner fitted only on out-of-fold predictions. On the held-out test set the proposed Updated SandBoilNet reaches an intersection-over-union of 0.707 over three seeds, against 0.608 for the published original re-evaluated on the same split. Under the stacking protocol the calibrated stack reaches 0.681 against 0.694 for the strongest fold-averaged member, so it does not improve on the best single model; eight meta-learner families reproduce that outcome, which we trace to a mean pairwise error correlation of 0.894 among members. A synthetic pool filtered for label fidelity lifts the champion to 0.718 over three seeds against a 0.707 control. We also introduce a mask-conditioned synthesis route that makes the conditioning mask the label by construction, giving labelled training images at zero annotation cost.
Comments24 pages, 17 figures, 14 tables. Supported by the U.S. Army Corps of Engineers under Contract No. W912HZ-23-2-0004
