Search papers, labs, and topics across Lattice.
This paper introduces SafeRestore, a framework that addresses the selective action problem in industrial image restoration by ranking restoration candidates based on action-specific fitted scores. The method evaluates the effectiveness of these candidates using a fixed gate determined by threshold-tuning data, ensuring that the restoration process does not compromise defect detection. In a study involving 4,591 images, SafeRestore demonstrated a significant risk-coverage behavior, although it revealed high evidence-loss incidences under certain conditions, highlighting the need for careful selection in restoration processes.
Restoration processes can inadvertently suppress defect detection, but SafeRestore offers a robust framework to audibly assess when to trust automated image transformations.
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.
