mlsanityData to 7 Oct 2026

SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restoration

arXiv 2609.03475 ↗First posted 3 Sep 2026cs.CV stat.APcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 30 of its 46 references that are in the map. First posted on arXiv 3 Sep 2026.

Builds on

30 of 46 references.

References · 30

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  2. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  3. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  4. 2017Enhanced Deep Residual Networks for Single Image Super-Resolutioncited by 1,543
  5. 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
  6. 2021Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Datacited by 961
  7. 2017Selective Classification for Deep Neural Networkscited by 799
  8. 2022Simple Baselines for Image Restorationcited by 701
  9. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  10. 2022Conformal Risk Controlcited by 290
  11. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 278
  12. 2020Consistent Estimators for Learning to Defer to an Expertcited by 262
18 more
  1. 2021Learn then Test: Calibrating Predictive Algorithms to Achieve Risk Controlcited by 256
  2. 2019Segmentation-Based Deep-Learning Approach for Surface-Defect Detectioncited by 145
  3. 2022Image-to-Image Regression with Distribution-Free Uncertainty Quantification and Applications in Imagingcited by 107
  4. 2018Task-Driven Super Resolution: Object Detection in Low-resolution Imagescited by 52
  5. 2018Crafting a Toolchain for Image Restoration by Deep Reinforcement Learningcited by 45
  6. 2019Path-Restore: Learning Network Path Selection for Image Restorationcited by 39
  7. 2025UniRestore: Unified Perceptual and Task-Oriented Image Restoration Model Using Diffusion Priorcited by 39
  8. 2024Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Losscited by 17
  9. 2025Selective Conformal Risk Controlcited by 10
  10. 2024Task-Driven Uncertainty Quantification in Inverse Problems via Conformal Predictioncited by 8
  11. 2026Conformal Selective Prediction with General Risk Controlcited by 8
  12. 2025LEC: Linear Expectation Constraints for Selection-Conditioned Risk Control in Selective Prediction and Routing Systemscited by 4
  13. 2026RACER: Risk-Aware Calibrated Efficient Routing for Large Language Modelscited by 4
  14. 2026A Joint Finite-Sample Certificate for Adaptive Selective Conformal Risk Controlcited by 3
  15. 2023Automated Semiconductor Defect Inspection in Scanning Electron Microscope Images: a Systematic Reviewcited by 2
  16. 2025Conformal Segmentation in Industrial Surface Defect Detection with Statistical Guaranteescited by 2
  17. 2025HalluGen: Synthesizing Realistic and Controllable Hallucinations for Evaluating Image Restorationcited by 1
  18. 2026Does Super-Resolution Preserve Defect Evidence? A Low-False-Call Benchmark for Semiconductor Inspectioncited by 1

Built on by

Not cited yet.