mlsanityData to 7 Oct 2026

Active Learning and Novel Model Calibration Measurements for Automated Visual Inspection in Manufacturing

arXiv 2209.05486 ↗First posted 12 Sep 2022cs.LG cs.AI cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Quality control is a crucial activity performed by manufacturing enterprises to ensure that their products meet quality standards and avoid potential damage to the brand's reputation. The decreased cost of sensors and connectivity enabled increasing digitalization of manufacturing. In addition, artificial intelligence enables higher degrees of automation, reducing overall costs and time required for defect inspection. This research compares three active learning approaches, having single and multiple oracles, to visual inspection. Six new metrics are proposed to assess the quality of calibration without the need for ground truth. Furthermore, this research explores whether existing calibrators can improve their performance by leveraging an approximate ground truth to enlarge the calibration set. The experiments were performed on real-world data provided by Philips Consumer Lifestyle BV. Our results show that the explored active learning settings can reduce the data labeling effort by between three and four percent without detriment to the overall quality goals, considering a threshold of p=0.95. Furthermore, the results show that the proposed calibration metrics successfully capture relevant information otherwise available to metrics used up to date only through ground truth data. Therefore, the proposed metrics can be used to estimate the quality of models' probability calibration without committing to a labeling effort to obtain ground truth data.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 20 of its 76 references that are in the map. First posted on arXiv 12 Sep 2022.

Builds on

20 of 76 references.

References · 20

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  3. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  4. 2018Computational Optimal Transportcited by 765
  5. 2020A Survey of Deep Active Learningcited by 547
  6. 2021CutPaste: Self-Supervised Learning for Anomaly Detection and Localizationcited by 529
  7. 2021DRAEM -- A discriminatively trained reconstruction embedding for surface anomaly detectioncited by 510
  8. 2019Measuring Calibration in Deep Learningcited by 443
  9. 2019Verified Uncertainty Calibrationcited by 307
  10. 2020Sub-Image Anomaly Detection with Deep Pyramid Correspondencescited by 297
  11. 2020Multivariate Confidence Calibration for Object Detectioncited by 98
  12. 2022DSR -- A dual subspace re-projection network for surface anomaly detectioncited by 89
8 more
  1. 2015A Review of Feature Selection Methods Based on Mutual Informationcited by 67
  2. 2021Distribution-free calibration guarantees for histogram binning without sample splittingcited by 44
  3. 2021Estimating Expected Calibration Errorscited by 24
  4. 2022Human-Centric Artificial Intelligence Architecture for Industry 5.0 Applicationscited by 11
  5. 2018Probability Calibration Treescited by 6
  6. 2021Active learning using weakly supervised signals for quality inspectioncited by 4
  7. 2021Streaming Machine Learning and Online Active Learning for Automated Visual Inspectioncited by 4
  8. 2021Towards Active Learning Based Smart Assistant for Manufacturingcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 1.

4 papers.

  1. 2023Bayesian Quadrature for Neural Ensemble Searchcited by 1
  2. 2023Human in the AI loop via xAI and Active Learning for Visual Inspectioncited by 1
  3. 2024A Data-Efficient Sequential Learning Framework for Melt Pool Defect Classification in Laser Powder Bed Fusioncited by 0
  4. 2025Calibrated Uncertainty Sampling for Active Learningcited by 0