The DOI matches its Crossref record; 46 of the 46 references it cites were found in a registry or an index; 11 of the 13 sources its claims cite were checked for support.
X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection
Open accessAbstract
It is important to accurately classify the defects in hot rolled steel strip since the detection of defects in hot rolled steel strip is closely related to the quality of the final product. The lack of actual hot-rolled strip defect data sets currently limits further research on the classification of hot-rolled strip defects to some extent. In real production, the convolutional neural network (CNN)-based algorithm has some difficulties, for example, the algorithm is not particularly accurate in classifying some uncommon defects. Therefore, further research is needed on how to apply deep learning to the actual detection of defects on the surface of hot rolled steel strip. In this paper, we proposed a hot rolled steel strip defect dataset called Xsteel surface defect dataset (X-SDD) which contains seven typical types of hot rolled strip defects with a total of 1360 defect images. Compared with the six defect types of the commonly used NEU surface defect database (NEU-CLS), our proposed X-SDD contains more types. Then, we adopt the newly proposed RepVGG algorithm and combine it with the spatial attention (SA) mechanism to verify the effect on the X-SDD. Finally, we apply multiple algorithms to test on our proposed X-SDD to provide the corresponding benchmarks. The test results show that our algorithm achieves an accuracy of 95.10% on the testset, which exceeds other comparable algorithms by a large margin. Meanwhile, our algorithm achieves the best results in Macro-Precision, Ma…
Overview
CoChat Summary
TL;DR
The paper introduces X-SDD, a hot-rolled steel strip surface defect dataset with seven defect types and 1,360 images, and benchmarks deep learning classifiers on it. It reports that RepVGG combined with spatial attention achieves 95.10% accuracy and the best Macro-Precision, Macro-Recall, and Macro-F1 among compared models.
Key findings
- X-SDD contains 1,360 defect images at 128 × 128 pixels in 3-channel JPG, covering seven defect types: 238 slag inclusions, 397 red iron sheet, 122 iron sheet ash, 134 surface scratches, 63 oxide scale of plate system, 203 finishing roll printing, and 203 oxide scale of temperature system. It has one more category than NEU-CLS (six types) and is imbalanced, with the largest class more than 6 times the smallest.
- RepVGG+SA achieves 95.10% accuracy, 93.92% Macro-Recall, 95.16% Macro-Precision, and 93.25% Macro-F1 on the 408-image test set; single RepVGG_B3g4 achieves 91.67% accuracy. Across compared algorithms, accuracy ranges 87.01–95.10%, Macro-Recall 82.04–93.92%, Macro-Precision 82.04–95.16%, and Macro-F1 81.58–93.25%.
- Per-class accuracy for RepVGG+SA: finishing roll printing 100%, oxide scale of plate system 78.95% (lowest), red iron sheet 94.12%, scratches 97.50%, inclusion 98.36%, iron sheet ash 83.78%, and oxide scale of temperature system 98.36%.
- Model complexity: RepVGG+SA has 83.825M parameters and 17.892 G MACs, compared with EspNet-v2 at 0.627M parameters and 0.090 G MACs.
Methods
- Dataset was collected from the hot rolled steel strip field; 70% was used as trainset (952 images) and 30% as testset (408 images). Images were resized to 224 × 224 pixels; training used 100 epochs, mini-batch 10, learning rate 0.0001, and Adam optimization on a single NVIDIA RTX2080S GPU, Intel Core i7-9700 CPU, 16GB RAM, Windows 10, and PyTorch.
- The proposed model is RepVGG_B3g4 combined with a spatial attention mechanism (RepVGG+SA), using RepVGG structural re-parameterization and a spatial attention module. It is compared against EspNet-v2, GhostNet, ShuffleNet, SqueezeNet, Xception, VGG16, ResNet50/101/152, RepVGG_B1g2, and RepVGG_B3g4.
- Evaluation metrics are Accuracy, Macro-Recall, Macro-Precision, and Macro-F1; macro metrics are obtained by treating the multiclass problem as multiple binary classification problems and averaging per-class Recall, Precision, and F1.
Limitations
- Stated: RepVGG+SA performs poorly on oxide scale of plate system, with only 78.95% accuracy; the authors attribute this to the relatively small sample size for that category and its morphological similarity to slag inclusion, suggesting more samples, cascade structure, or artificial prior knowledge as possible improvements.
- Stated: RepVGG+SA is computationally costly, with 83.825M parameters and 17.892 G MACs, much larger than EspNet-v2 (0.627M, 0.090 G); future work aims to reduce computational complexity.
- Evident from the text: X-SDD is imbalanced (largest class more than 6 times the smallest) and relatively small (1,360 images from a single hot-rolled strip source); no cross-dataset training or evaluation on NEU-CLS is reported, only dataset comparison.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures









Verification
Claims the paper makes
7 Valid · 5 Not valid · 2 Not checked · 54 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“Existing hot rolled strip lines are usually equipped with surface defect detection systems that can detect defects on the strip surface [6]; however, unfortunately, the system is less accurate in classifying defects.”
§ X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection > 1. Introduction
What the sources say
- Supportedcites [6] Luo, 2019, Surface Defect Classification for Hot-Rolled Steel Strips by Selectively Dominant Local Binary Patterns, IEEE Access source
The Introduction reports that defect detection has made substantial progress but says surface defect classification has “much improvement space” and describes high-accuracy classification as a continuing obstacle. This supports the citing sentence’s broad characterization of existing systems’ classification performance. (LLM, conf=0.88)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Compared with the six defect types of the commonly used NEU surface defect database (NEU-CLS), our proposed X-SDD contains more types.”
- Also stated in: § 3.2. The Comparison between Xsteel Surface Defect Dataset and NEU Surface Defect Database · plain
“The NEU-CLS contains six types of defects, while the X-SDD we proposed contains seven types of defects.”
§ X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection > Abstract
What the sources say
- Could not verifycites [31] Song, 2013, Micro Surface defect detection method for silicon steel strip based on saliency convex active contour model, Math. Probl. Eng. sourceExperimental — accuracy not yet measured
Sections 4.2 and 4.3 discuss spot defects and steel-pit defects, but do not give a defect-type count for NEU-CLS or X-SDD. Searches for “NEU-CLS six defect types” and “X-SDD seven defect types” found no passage in our copy addressing the comparison. Page numbers were not available. (LLM, conf=0.76)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 3.2. The Comparison between Xsteel Surface Defect Dataset and NEU Surface Defect Database · plain
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In this paper, the model achieves results second only to our proposed RegVGG+SA model in both Accuary and Macro-Precision metrics.”
- Also stated in: § 6. Discussion and Conclusions · plain
“The comparison results show that ResNet50, used in the literature [41], achieves results on Accuracy and Macro-Precision that are second only to our proposed RepVGG+SA algorithm.”
§ X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection > 5.2. Experimental Results
What the sources say
- Partly supportedcites [41] Konovalenko, I., Maruschak, P., Brezinová, J., Viňáš, J., and Brezina, J. (2020). Steel Surface Defect Classification Using Deep Residual Neural Network. Metals, 10. sourceExperimental — accuracy not yet measured
The Methodology and Conclusions (pages unavailable) describe a ResNet50 classifier for steel-surface defects and report its classification accuracy; the Training section also identifies precision as a measured metric. The paper does not report results on X-SDD or compare ResNet50 with RepVGG+SA, so it does not support the claimed second-place ranking on Accuracy and Macro-Precision. (LLM, conf=0.85)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 6. Discussion and Conclusions · plain
Every source the paper cites for this claim was checked and supports it.
In the paper
“The excellent performance of ResNet50 in strip classification indicates that the residual network has some advantages in the classification of strip defects.”
§ X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection > 6. Discussion and Conclusions
What the sources say
- Supportedcites [41] Konovalenko, I., Maruschak, P., Brezinová, J., Viňáš, J., and Brezina, J. (2020). Steel Surface Defect Classification Using Deep Residual Neural Network. Metals, 10. source
The Conclusions report that the ResNet50 classifier achieved 0.9691 average accuracy on surface defects in rolled metal and performed better on test data than the other ResNet depths examined. The Methodology also describes how residual connections enable deeper networks and better performance, supporting the stated inference about advantages for defect classification. (LLM, conf=0.90)
hedgedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Our test results demonstrate the effectiveness of the ResNet50 model used in [41]”
§ X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection > 5.2. Experimental Results
What the sources say
- Supportedcites [41] Konovalenko, I., Maruschak, P., Brezinová, J., Viňáš, J., and Brezina, J. (2020). Steel Surface Defect Classification Using Deep Residual Neural Network. Metals, 10. source
The citation identifies the ResNet50 model used in the source, rather than attributing the citing authors’ test results to it. The source’s Methodology section describes its ResNet50 classifier, and its Conclusions report results for that model. (LLM, conf=0.93)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
36 more claims
Create a free account to see all 68 claims and every source verdict.
- Probably not a substantial claim. 13
- It may state two separate claims as one. 15
- The quote only partly states this claim. 3
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 10×
“In addition, ResNet50 performs better on X-SDD than the deeper ResNet101 and 152, indicating that the deeper the network level is not better when the amount of data is not particularly large.”
BackgroundInfluentialVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148 · cited 1×
“…defect classification networks tend to use off-the-shelf deep learning network structures and their various variants, including AlexNet [23], VGGNet [24], GoogleNet [25], ResNet [26], DenseNet [27], SENet [28], Shuf-fleNet [29] and MobileNet [30], etc. Compared with traditional algorithms such as…”
MethodImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566 · cited 2×
“In general, existing strip surface defect classification networks tend to use off-the-shelf deep learning network structures and their various variants, including AlexNet [23], VGGNet [24], GoogleNet [25], ResNet [26], DenseNet [27], SENet [28], Shuf-fleNet [29] and MobileNet [30], etc. Compared with traditional algorit…”
BackgroundGoing deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562 · cited 2×
“In general, existing strip surface defect classification networks tend to use off-the-shelf deep learning network structures and their various variants, including AlexNet [23], VGGNet [24], GoogleNet [25], ResNet [26], DenseNet [27], SENet [28], Shuf-fleNet [29] and MobileNet [30], etc. Compared with traditional algorit…”
BackgroundAn Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667 · cited 2×
“In general, existing strip surface defect classification networks tend to use off-the-shelf deep learning network structures and their various variants, including AlexNet [23], VGGNet [24], GoogleNet [25], ResNet [26], DenseNet [27], SENet [28], Shuf-fleNet [29] and MobileNet [30], etc. Compared with traditional algorit…”
BackgroundCBAM: Convolutional Block Attention Module
Woo, S., Park, J., Lee, J.-Y., & Kweon, I. S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_1 · Cited by 25,853 · cited 3×
“According to [40], max pooling and average pooling are used in channel dimension to get two different feature descriptions FS avg ∈ R1×H×W and FS max ∈ R1×H×W .”
BackgroundMethodInfluentialMobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
Research works printed but not linked: 4
- Aldunin, 2017, Development of method for calculation of structure parameters of hot-rolled steel strip for sheet stamping, J. Chem. Technol. Metall., 52, 737
- (2021, January 18). Severstal is Mastering the Production of Video Inspection Systems for Rolled Surfaces. Available online: https://metallurgprom.org/en/press-releases/4952-severstal-osvaivaet-izgotovlenie-sistem-videoinspekcii-poverhnosti-prokata.html.
- Zaghdoudi, R., Seridi, H., and Boudiaf, A. (2019, January 24–25). Multiple classifier combination for steel surface inspection. Proceedings of the 2nd Conference on Informatics and Applied Mathematics, IAM 2019, Guelma, Algeria.
- Amid, 2012, Enhanced performance for support vector machines as multi-class classifiers in steel surface defects detection, World Acad. Sci. Eng. Technol., 6, 1096
Cited by
Khanam, R., Hussain, M., Hill, R., & Allen, P. (2024) · IEEE Access · doi:10.1109/access.2024.3425166 · Cited by 237
“Feng et al. [316] address the critical challenge of automating hot-rolled steel strip defect detection, highlighting its crucial role in various manufacturing industries.”
BackgroundSteel Surface Defect Recognition: A Survey
Wen, X., Shan, J., He, Y., & Song, K. (2022) · Coatings · doi:10.3390/coatings13010017 · Cited by 210
Bai, D., Li, G., Jiang, D., Yun, J., Tao, B., Jiang, G., Sun, Y., & Ju, Z. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107697 · Cited by 116
A ResNet50-Based Method for Classifying Surface Defects in Hot-Rolled Strip Steel
Feng, X., Gao, X., & Luo, L. (2021) · Mathematics · doi:10.3390/math9192359 · Cited by 99
“The X-SDD dataset contains 7 types of 1360 surface defects in hot rolled strip: 238 slag inclusions, 397 red iron sheet, 122 iron sheet ash, 134 surface scratches, 63 oxide scale of plate system, 203 finishing roll printing and 203 oxide scale of temperature system. the size of original images is 128 × 128 pixels with…”
BackgroundMethodInfluentialSelf-citationCross Position Aggregation Network for Few-Shot Strip Steel Surface Defect Segmentation
Feng, H., Song, K., Cui, W., Zhang, Y., & Yan, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3246519 · Cited by 84
Metadata
- Authors
- Feng, X., Gao, X., & Luo, L.
- Affiliations
- Northeastern University (CN)
- Corresponding author
- Gao, Xianwen
- Venue
- Symmetry
- Publisher
- MDPI AG
- Published
- 2021-04-17
- Volume
- 13
- Issue
- 4
- Pages
- 706
- ISSN
- 2073-8994 (ISSN-L)
- OpenAlex
- W3153037112
- Cited by
- 158
- References
- 40
- Citations by year
- 2026: 22 · 2025: 27 · 2024: 50 · 2023: 29 · 2022: 23 · 2021: 7
- FWCI
- 14.10
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Symmetry (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (61573087, 61573088)
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Engineering › Mechanical Engineering › Non-Destructive Testing Techniques
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Keywords
- hot-rolled strip, surface defect detection, defect classification, benchmark dataset, RepVGG, spatial attention mechanism, steel quality inspection
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection. https://app.cochat.ai/papers/10.3390/sym13040706
- The paper
- Feng, X., Gao, X., & Luo, L. (2021). X-SDD: A New Benchmark for Hot Rolled Steel Strip Surface Defects Detection. Symmetry. https://doi.org/10.3390/sym13040706
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.