Mixed supervision for surface-defect detection: From weakly to fully supervised learning
Open accessThe claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Božić et al. find that a small number of pixel-level annotations can help the model achieve performance comparable to full supervision.
“Bo ž i č et al. [120] find that a small number of pixel-level annotations can help the model achieve performance comparable to full supervision.”
From Deep Industrial Image Anomaly Detection: A Survey (2024) · cites this paper as [120]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 50 · Cited by 377
Research works printed but not linked: 5
- I. Goodfellow, J. Pouget-Abadie, and M. Mirza. Genera- tive Adversarial Networks. In Neural Information Process- ing Systems, pages 1-9, 2014. 3
- Y. Huang, C. Qiu, X. Wang, S. Wang, and K. Yuan. A com- pact convolutional neural network for surface defect inspec- tion. Sensors, 20(7), 2020. 2, 3, 7
- D. Pathak, P. Krähenbühl, and T. Darrell. Constrained Con- volutional Neural Networks for Weakly Supervised Segmen- tation Multi-class Image Segmentation. In International Conference on Computer Vision, pages 1-28, 2015. 3
- D. Tabernik, S. Šela, J. Skvarč, and D. Skočaj. Segmentation-based deep-learning approach for surface- defect detection. Journal of Intelligent Manufacturing, pages 1-18, 2019. 1, 2, 3, 4, 6, 7
- R. Zhang, P. Isola, and A. A. Efros. Split-Brain Autoen- coders: Unsupervised Learning by Cross-Channel Predic- tion. In Computer Vision and Pattern Recognition, pages 645-654, 07 2017. 3
- Authors
- Božič, J., Tabernik, D., & Skočaj, D.
- Affiliations
- University of Ljubljana (SI)
- Corresponding author
- Božič, Jakob
- Venue
- Computers in Industry
- Publisher
- Elsevier BV
- Published
- 2021-08
- Volume
- 129
- Pages
- 103459
- ISSN
- 0166-3615 (ISSN-L)
- OpenAlex
- W3153381206
- Cited by
- 377
- References
- 50
- Citations by year
- 2026: 78 · 2025: 101 · 2024: 92 · 2023: 64 · 2022: 34 · 2021: 8
- FWCI
- 25.61
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- Computers in Industry (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- ARRS
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- surface defect detection, mixed supervision, weakly supervised learning, industrial inspection, defect segmentation, defect classification, image-level labels, annotation cost reduction, steel defect detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
