发表机构
Santa Clara University（圣克拉拉大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出SafeRestore框架，用于选择性工业图像复原的风险审计，可在自动返回图像与复审间决策，经Carinthia-S等数据集验证，部分策略可满足风险覆盖要求。
AI 中文摘要
工业检测流程通常会在检测器对图像进行处理前先复原测量图像，但复原操作可能会抑制检测器所依赖的缺陷结构，或在干净区域产生激活信号。我们将复原问题建模为针对测量显示、5个复原候选结果及复审的选择性动作问题。SafeRestore采用动作特定的拟合分数对候选结果排序，在阈值调整数据上设置门限，并在不相交的证书样本上评估该固定门限，使用两个单侧精确二项式边界：一个用于正条件下的证据损失发生率，另一个用于所有接受结果的过度激活发生率。该保证针对在观测其证书结果前已固定的策略，在图像级独立同分布工作模型下具有边际性。在对4591张公开Carinthia-S图像的回顾性拆分样本研究中，该协议产生了可审计的风险-覆盖行为。主要全动作策略在5次训练重复中通过了1次（当故障计为零时，门控测试覆盖度为12.0%±26.9%），而固定双三次及低复杂度变体通过次数更多。在保留形态学数据上，证据损失发生率升至81.1%-90.3%，KolektorSDD数据集既缺乏检测器能力，也没有足够的正类证书图像以满足所述目标。因此，本研究的贡献是一个可审计的、与检测器相关的框架，用于决定何时可自动返回转换后的图像、何时仍需复审——而非声称自适应路由在当前证据下优于更简单的策略。
英文摘要
Industrial inspection pipelines often restore a measured image before a detector acts on it, yet restoration can suppress detector-supported defect structure or create clean-region activations. We formulate restoration as a selective action problem over the measured display, five restored candidates, and review. SafeRestore ranks candidates with action-specific fitted scores, chooses a gate on threshold-tuning data, and evaluates the fixed gate on a disjoint certification sample with two one-sided exact binomial bounds: one for the positive-conditional evidence-loss incident rate and one for the all-accepted excess-activation incident rate. The guarantee is marginal for one policy fixed before its certification outcomes are observed, under an image-level i.i.d. working model. In a retrospective split-sample study of 4,591 public Carinthia-S images, the protocol yields auditable risk-coverage behavior. The primary all-action policy passes in one of five training repetitions (12.0% +/- 26.9% pass-gated test coverage when failures count as zero), whereas fixed bicubic and reduced-complexity variants pass more often. On reserved morphologies, evidence-loss incidence rises to 81.1-90.3%, and KolektorSDD lacks both detector competence and enough positive certification images for the stated target. The contribution is therefore an auditable, detector-relative framework for deciding when a transformed image may be returned automatically and when review remains necessary -- not a claim that adaptive routing outperforms simpler policies on the present evidence.
Comments27 pages, 10 figures, 6 main-text tables, and 17 supplementary tables. Shares the Carinthia-S image identities with arXiv:2607.17401 by the same authors; the overlap and the distinct estimand are stated in Section 2.4 and Table 1
