# Conformal Segmentation in Industrial Surface Defect Detection with Statistical Guarantees

arXiv: https://arxiv.org/abs/2504.17721 · HTML: https://mlsanity.com/paper/2504.17721/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 26 references that are in the map.
- First posted on arXiv 24 Apr 2025.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Conformal prediction beyond exchangeability](https://mlsanity.com/paper/2202.13415/) (2022)
- [Conformal Risk Control](https://mlsanity.com/paper/2208.02814/) (2022)
- [ConU: Conformal Uncertainty in Large Language Models with Correctness Coverage Guarantees](https://mlsanity.com/paper/2407.00499/) (2024)
- [SConU: Selective Conformal Uncertainty in Large Language Models](https://mlsanity.com/paper/2504.14154/) (2025)
- [Confident Object Detection via Conformal Prediction and Conformal Risk Control: an Application to Railway Signaling](https://mlsanity.com/paper/2304.06052/) (2023)
- [Conformal Semantic Image Segmentation: Post-hoc Quantification of Predictive Uncertainty](https://mlsanity.com/paper/2405.05145/) (2024)
- [Sample then Identify: A General Framework for Risk Control and Assessment in Multimodal Large Language Models](https://mlsanity.com/paper/2410.08174/) (2024)
- [Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond](https://mlsanity.com/paper/2402.14259/) (2024)
- [GhostNetV3: Exploring the Training Strategies for Compact Models](https://mlsanity.com/paper/2404.11202/) (2024)
- [Conformal Risk Control for Pulmonary Nodule Detection](https://mlsanity.com/paper/2412.20167/) (2024)

## Built on by (most cited first, 2 of 2)

- [Distribution-Free Process Monitoring with Conformal Prediction](https://mlsanity.com/paper/2512.23602/) (2025)
- [SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image Restoration](https://mlsanity.com/paper/2609.03475/) (2026)

## Abstract (arXiv)

In industrial settings, surface defects on steel can significantly compromise its service life and elevate potential safety risks. Traditional defect detection methods predominantly rely on manual inspection, which suffers from low efficiency and high costs. Although automated defect detection approaches based on Convolutional Neural Networks(e.g., Mask R-CNN) have advanced rapidly, their reliability remains challenged due to data annotation uncertainties during deep model training and overfitting issues. These limitations may lead to detection deviations when processing the given new test samples, rendering automated detection processes unreliable. To address this challenge, we first evaluate the detection model's practical performance through calibration data that satisfies the independent and identically distributed (i.i.d) condition with test data. Specifically, we define a loss function for each calibration sample to quantify detection error rates, such as the complement of recall rate and false discovery rate. Subsequently, we derive a statistically rigorous threshold based on a user-defined risk level to identify high-probability defective pixels in test images, thereby constructing prediction sets (e.g., defect regions). This methodology ensures that the expected error rate (mean error rate) on the test set remains strictly bounced by the predefined risk level. Additionally, we observe a negative correlation between the average prediction set size and the risk level on the test set, establishing a statistically rigorous metric for assessing detection model uncertainty. Furthermore, our study demonstrates robust and efficient control over the expected test set error rate across varying calibration-to-test partitioning ratios, validating the method's adaptability and operational effectiveness.