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 112
FaNet: Feature-aware network for few shot classification of strip steel surface defects
Zhao, W., Song, K., Wang, Y., Liang, S., & Yan, Y. (2023) · Measurement · doi:10.1016/j.measurement.2023.112446 · Cited by 75
Cui, W., Song, K., Feng, H., Jia, X., Liu, S., & Yan, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3290965 · Cited by 81
“Based on the SD-900 dataset, we obtain most strip surface defect images from the open-source X-SDD [62] and GC10-DET [63], which are taken in the production and manufacturing stages.”
MethodHao, Z., Li, Z., Ren, F., Lv, S., & Ni, H. (2022) · Metals · doi:10.3390/met12020311 · Cited by 46
“Introduction to the Data Set The X-SDD data set [31] contains 1360 strip steel surface defect images in 7 categories.”
MethodLiu, H., Chen, C., Hu, R., Bin, J., Dong, H., & Liu, Z. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3346470 · Cited by 48
“Feng et al. [18] adopted a scheme combining the RepVGG algorithm and spatial attention mechanism to recognize surface defects on hot-rolled strips.”
MethodUnveiling Patterns: A Study on Semi-Supervised Classification of Strip Surface Defects
Liu, Y., Yang, H., & Wu, C. (2023) · IEEE Access · doi:10.1109/access.2023.3326843 · Cited by 54
A Survey of Vision-Based Methods for Surface Defects’ Detection and Classification in Steel Products
Ibrahim, A. A. M. S., & Tapamo, J. (2024) · Informatics · doi:10.3390/informatics11020025 · Cited by 70
Cross-supervised contrastive learning domain adaptation network for steel defect segmentation
Zhao, L., Zhang, Y., Duan, J., & Yu, J. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102964 · Cited by 44
Large scale foundation models for intelligent manufacturing applications: a survey
Zhang, H., Semujju, S. D., Wang, Z., Lv, X., Xu, K., Wu, L., Jia, Y., Wu, J., Liang, W., Zhuang, R., et al. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02536-7 · Cited by 83
Bouguettaya, A., & Zarzour, H. (2024) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-024-13341-0 · Cited by 39
“Feng et al. [33] introduced a novel hot-rolled steel strip surface defect dataset called the Xsteel surface defect dataset (X-SDD).”
An imbalanced small sample slab defect recognition method based on image generation
Fu, T., Li, P., & Liu, S. (2024) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2024.03.028 · Cited by 46
Detection and classification of surface defects on hot-rolled steel using vision transformers
Vasan, V., Sridharan, N. V., Sugumaran, V., & Aghaei, M. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e38498 · Cited by 53
“Admittedly, the RepVGG algorithm proposed by Feng et al. with spatial attention provision for operation on the X-SDD data set achieved just over 95 % classification accuracy [51].”
MethodSteel Strip Surface Defect Detection Method Based on Improved YOLOv5s
Lu, J., Zhu, M., Ma, X., & Wu, K. (2024) · Biomimetics · doi:10.3390/biomimetics9010028 · Cited by 36
“X. Feng et al. [4] used RepVGG (Making VGG-style ConvNets Great Again) in combination with SA (spatial attention) spatial attention to achieve good results in strip defect detection.”
MethodAn efficient detector for detecting surface defects on cold-rolled steel strips
Chen, S., Jiang, S., Wang, X., Sun, P., Hua, C., & Sun, J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109325 · Cited by 43
Surface Defect Detection of Strip-Steel Based on an Improved PP-YOLOE-m Detection Network
Zhang, Y., Liu, X., Guo, J., & Zhou, P. (2022) · Electronics · doi:10.3390/electronics11162603 · Cited by 31
Fang, W., Huang, J., Peng, T., Long, Y., & Yin, F. (2024) · Journal of Iron and Steel Research International · doi:10.1007/s42243-024-01179-5 · Cited by 35
Contrastive self-supervised representation learning framework for metal surface defect detection
Zabin, M., Kabir, A. N. B., Kabir, M. K., Choi, H., & Uddin, J. (2023) · Journal Of Big Data · doi:10.1186/s40537-023-00827-z · Cited by 32
“In [37], the RepVGG algorithm with spatial attention was applied to hot-rolled SSDD, showcasing improved classification performance compared to ResNet, VGG, and MobileNet.”
MethodZheng, X., Liu, W., & Huang, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3349628 · Cited by 26
“The formulas of these measures can be found in literature [4].”
BackgroundMethodInfluentialA Review and Benchmark on State-of-the-Art Steel Defects Detection
Chazhoor, A. A. P., Ho, E. S. L., Gao, B., & Woo, W. L. (2023) · SN Computer Science · doi:10.1007/s42979-023-02436-2 · Cited by 41
“The benchmark paper by the authors of [10] introduced a novel Xsteel surface defect dataset (X-SDD) and analyzed the performance of various models.”
BackgroundStrip Steel Defect Classification Using the Improved GAN and EfficientNet
Guan, S., Chang, J., Shi, H., Xiao, X., Li, Z., Wang, X., & Wang, X. (2021) · Applied Artificial Intelligence · doi:10.1080/08839514.2021.1995231 · Cited by 25
Li, Z., Li, B., Ni, H., Ren, F., Lv, S., & Kang, X. (2022) · Metals · doi:10.3390/met12111809 · Cited by 29
“[30] proposed RepVGG_B3g4 + SA by combining RepVGG with a spatial attention module.”
MethodLightweight defect detection network based on steel strip raw images
Huang, Y., Chen, Z., Chen, Z., Zhou, D., & Pan, E. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110179 · Cited by 26
Classification and Fast Few-Shot Learning of Steel Surface Defects with Randomized Network
Nagy, A. M., & Czúni, L. (2022) · Applied Sciences · doi:10.3390/app12083967 · Cited by 30
Konovalenko, І. V., Maruschak, P. O., Kozbur, H., Brezinová, J., Brezina, J., & Guzanová, A. (2021) · Metals · doi:10.3390/met11111851 · Cited by 22
Adaptive-MAML: Few-shot metal surface defects diagnosis based on model-agnostic meta-learning
Pang, S., Zhang, L., Yuan, Y., Zhao, W., Wang, S., & Wang, S. (2023) · Measurement · doi:10.1016/j.measurement.2023.113612 · Cited by 26
Jia, H., Cai, D., Yang, J., et al. (2023) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-023-00537-0 · Cited by 21
“For defect detection tasks, the dataset provides annotations indicating the category and location of defects in each image [21].”
MethodA Survey on Surface Defect Inspection Based on Generative Models in Manufacturing
He, Y., Li, S., Wen, X., & Xu, J. (2024) · Applied Sciences · doi:10.3390/app14156774 · Cited by 35
Current Trends on Deep Learning Techniques Applied in Iron and Steel Making Field: A Review
Tsutsui, K., Namba, T., Kihara, K., Hirata, J., Matsuo, S., & Ito, K. (2024) · ISIJ International · doi:10.2355/isijinternational.isijint-2024-098 · Cited by 23
Enhanced multiscale attentional feature fusion model for defect detection on steel surfaces
Xia, Y., Lu, Y., Jiang, X., & Xu, M. (2024) · Pattern Recognition Letters · doi:10.1016/j.patrec.2024.11.024 · Cited by 21
Wen, L., Zhang, Y., Gao, L., Li, X., & Li, M. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3271743 · Cited by 21
“…dataset, several methods are selected for the comparison, and they are fusing convolutional Siamese neural network (FCSNN) [36], ResNet50 with the addition of FcaNet and CBAM (RC-FcaNet) [37], surface defect data augmentation (SDDA) [16], and RepVGG algorithm with SA mechanism (RepVGG + SA) [38].”
MethodHussain, M., & Hill, R. C. (2023) · IEEE Access · doi:10.1109/access.2023.3283596 · Cited by 19
“Feng et al. [29] look at the automation of Hot rolled steel strip defects due to its impact on various industries including manufacturing.”
BackgroundSteel Strip Quality Assurance With YOLOV7-CSF: A Coordinate Attention and SIoU Fusion Approach
Raj, G. D., & Prabadevi, B. (2023) · IEEE Access · doi:10.1109/access.2023.3333894 · Cited by 22
“More detailed information can be found in [15] and [16].”
BackgroundResilient machine learning for steel surface defect detection based on lightweight convolution
Liu, L., Zhang, Y., & Karimi, H. R. (2024) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-024-14403-z · Cited by 23
Hussain, T., Hong, J., & Seok, J. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.050884 · Cited by 25
Wavelet Texture Descriptor for Steel Surface Defect Classification
Belila, D., Khaldi, B., & Aiadi, O. (2024) · Materials · doi:10.3390/ma17235873 · Cited by 19
“In another noteworthy study, Feng et al. [24] combined the RepVGG algorithm with a spatial attention mechanism, introducing the Xsteel Surface Defect Dataset (X-SDD) to focus on subtle defect characteristics.”
Review of Industry Workpiece Classification and Defect Detection using Deep Learning
Chen, C., Abdullah, A. B., Kok, S. H., & Tien, D. T. K. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.0130439 · Cited by 21
“Perceivably, the model prediction impact was associated with the model itself and the dataset [13].”
MethodCollaborative Filter Pruning for Efficient Automatic Surface Defect Detection
Wang, H., Fan, X. N., Ling, P., Wang, B., Chen, H., & Jin, Y. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3288208 · Cited by 17
“Moreover, we compare pruned models obtained by the CFP with recent SOTA defect classification methods [8], [9], [25], [38], [39] on the ELPV-DC, GC10-DET, and X-SDD datasets.”
BackgroundMethodInfluentialSteel surface defect recognition using classifier combination
Zaghdoudi, R., Bouguettaya, A., & Boudiaf, A. (2024) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-024-13407-z · Cited by 22
STE-YOLO: A Surface Defect Detection Algorithm for Steel Strips
Li, D., Wang, E., Li, Z., Yin, Y., Zhang, L., & Zhao, C. (2024) · Electronics · doi:10.3390/electronics14010054 · Cited by 18
Crop-paste and diffusion-based semi-supervised segmentation network for metal defect detection
Zhao, L., & Yu, J. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113573 · Cited by 18
Improved YOLOv5 Network for Steel Surface Defect Detection
Huang, B., Liu, J., Liu, X., Liu, K., Liao, X., Li, K., & Wang, J. (2023) · Metals · doi:10.3390/met13081439 · Cited by 21
Lin, L., Wang, Y., Zhao, S., Liu, J., Zhang, S., & Zhang, G. (2022) · Journal of Electronic Imaging · doi:10.1117/1.jei.31.6.063056 · Cited by 15
“The hot-rolled strip dataset named xsteel surface defect dataset (X-SDD) is employed, 35 which has the category labels of the defects but does not label the specific location information of the defects in the images, as shown in Fig.”
MethodWang, T., Li, Z., Xu, Y. W., Chen, J., Genovese, A., Piuri, V., & Scotti, F. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3315404 · Cited by 22
TSEDNet:Task-specific encoder–decoder network for surface defects of strip steel
Guo, Y., Wei, J., & Feng, X. (2024) · Measurement · doi:10.1016/j.measurement.2024.115438 · Cited by 22
Self-citationZhang, H., Liu, H., Guo, R., Liu, Q., Liang, L., Ma, W., & Liu, D. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3488000 · Cited by 14
“It, collected and made by Song et al., is derived from multiple sources, including NEU-CLS [44], X-SDD [45], and GC10-DET [46].”
Ma, Y., & Zhang, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112741 · Cited by 18
Feng, X., Gao, X., & Luo, L. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2082/1/012016 · Cited by 13
“X Feng et al [6] used the RepVGG model as the base classifier and added spatial attention to enhance the classification ability of the original model, and the improved model achieved the best results in terms of accuracy, recall, and other metrics.”
MethodSelf-citationXu, Y. W., Chen, J., Liang, Y., Zhai, Y., Ying, Z., Zhou, W., Genovese, A., Piuri, V., & Scotti, F. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3249221 · Cited by 15
“4(a) and (b) for generating images of 256 × 256 (NEU-CLS [36], X-SDD [37], and GC10 [38]) and 64 × 64 (NEU-CLS-64 [36]), respectively.”
BackgroundMethodZero-shot learning and classification of steel surface defects
Abdo, A. M. A. N., & Czúni, L. (2022) · International Conference on Machine Vision · doi:10.1117/12.2623570 · Cited by 12
Deng, Y., & Song, Y. (2023) · ISIJ International · doi:10.2355/isijinternational.isijint-2023-118 · Cited by 13
Li, Z., Gao, L., Li, X., & Gao, Y. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102527 · Cited by 11
Xu, M., Wei, J., & Feng, X. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109469 · Cited by 14
Self-citationChaudhry, N. J., Khan, M. B., Iqbal, M. J., & Yasir, S. M. (2022) · Journal on artificial intelligence · doi:10.32604/jai.2022.038875 · Cited by 18
“The major problems in manual processes [1] are as follows: • The steel manufacturing companies are continuously 24 h in operational so quality control staff have to work at awkward timing like late at night.”
BackgroundZeng, W., Wang, J., Chen, P., Zhong, Z., Hu, G., & Bao, W. (2024) · Signal Image and Video Processing · doi:10.1007/s11760-024-03270-6 · Cited by 14
Lin, L., Wen, A., Wang, Y., Zhao, S., Zhang, S., Yan, J., Zhou, Y. H., & Zhou, W. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad5b7c · Cited by 11
“We used two publicly available steel surface defect datasets X-SDD [34] and NEU-DET [35] in our experiments.”
Lightweight-detection: The strip steel surface defect identification based on improved YOLOv5d
Lu, Y., Huang, Z.-C., Jiang, Y., Liu, G., Wang, J., & Ma, Q. (2024) · Materials Today Communications · doi:10.1016/j.mtcomm.2024.109814 · Cited by 21
Fu, R., Huang, Z., Cao, M., Novák, D., Xie, C., & Huang, J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111521 · Cited by 9
Madhavan, S., Sridharan, N. V., Mahanta, T. K., & Sugumaran, V. (2024) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-024-09744-6 · Cited by 11
“…MSMP using ResNet50 94.73 [59] Ensemble DNN ResNet50 with FcaNet and CBAM 94.80 [60] RepVGG algorithm with spatial attention ( ) on X-SDD set 95.10 [61] Ensemble DNN combining ResNet50 and ResNet152 96.70 [62] Faster R-CNN 97.00 [63] Faster R-CNN with SPP, FPN, and matrix NMS 98.20 [64] IMN-YOLOV3…”
InfluentialGong, K., Ding, X., Guo, F., Wang, Z., Zhang, F., & He, C. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3598383 · Cited by 8
“FSC-20 is constructed by selecting and integrating samples from three widely used datasets: NEU-CLS, Xiangtan Steel Surface Defect Dataset (X-SDD) [45], and GC10-DET [46].”
Gong, L., Dong, H., Zhang, X., Cheng, X., Ye, F., Guo, L., & Ge, Z. (2024) · Journal of Electronic Imaging · doi:10.1117/1.jei.33.3.033001 · Cited by 11
“Feng et al. 24 proposed a solution combining the RepVGG algorithm and spatial attention mechanism to achieve surface defect identification of hot-rolled steel strips.”
MethodWu, H., Luo, Z., Sun, F., et al. (2024) · Sensors · doi:10.3390/s24123932 · Cited by 8
“At present, the neural networks commonly used in target detection are R-CNN, Fast R-CNN and YOLO [12,13].”
MethodContinual learning for surface defect segmentation by subnetwork creation and selection
Dekhovich, A., & Bessa, M. A. (2024) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02393-4 · Cited by 11
“For instance, after Song and Yan (2013) proposed their NEU-DET dataset with Hot Rolled Steel Strip Surface defects, containing six types of defects, other groups collected datasets with either different defect categories or a more significant number of defects, e.g., GC10-DET (Lv et al., 2020) and X-SDD (Feng et al., 2…”
Lin, L., Zhao, S., Zhang, Y., Wen, A., Zhang, S., Yan, J., Wang, Y., & Zhou, Y. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3404053 · Cited by 7
“…of our DA strategy and classification model, we conducted experiments using three real industrial defect datasets: 1) the Tianchi Alu-minum Profile Surface Defect Dataset (Tianchi) [24], 2) Xsteel Surface Defect Dataset (X-SDD) [25], and 3) Surface Defect Saliency-GT Dataset (SDS-GTD) [26].”
MethodDEENet: an edge-enhanced CNN–Transformer dual-encoder model for steel surface defect detection
Pan, W., Zhong, R., Huang, J., Li, Y., Zhang, W., Liu, T., & Liu, Y. (2026) · Scientific Reports · doi:10.1038/s41598-026-36390-9 · Cited by 9
Learning-Based Approach for Automated Surface Inspection with Industrial Tomography Imaging
Saied, M., Ali, R., Francis, C., Radilla, G., & Noun, Z. (2024) · Journal of Nondestructive Evaluation Diagnostics and Prognostics of Engineering Systems · doi:10.1115/1.4065428 · Cited by 7
Zhang, H., Liu, H., Guo, R., Liang, L., Liu, Q., & Ma, W. (2024) · Sensors · doi:10.3390/s24144630 · Cited by 12
“Figure 6 displays a partial sample of this dataset, which comprises 10 hot-rolled defects (6 types are sourced from the NEU-CLS dataset [50] and 4 types are sourced from the X-SDD dataset [51]) and 10 cold-rolled defects (sourced from the GC10-DET dataset [52]), each with 50 samples.”
MethodZhang, H., Liu, H., Guo, R., Zheng, C., Liu, Q., Liang, L., Ma, W., Liu, D., & Zhang, Y. M. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3598394 · Cited by 17
“5(a), FSC-20 comprises ten types of hot-rolled defects (from X-SDD [34] and NEU-CLS [35]) and ten types of cold-rolled defects (from GC10-DET [36]), with 50 samples for each defect category.”
High-resolution image-based surface defect detection method for hot-rolled strip steel
Feng, X., Gao, X., & Luo, L. (2022) · Journal of Electronic Imaging · doi:10.1117/1.jei.31.3.033020 · Cited by 6
Self-citationLiu, B., Wu, Q., Li, Z., & Chen, X. (2021) · Symmetry · doi:10.3390/sym13101844 · Cited by 8
“Based on the above formula, we get the Accuracy, Macro-Precision, Macro-Recall, and Macro-F1 formulas for multiple classifications [39]:”
MethodImprovements to YOLOv4 for Steel Surface Defect Detection
Cheng, Y., & Wang, S. (2022) · doi:10.1109/icoias56028.2022.9931299 · Cited by 6
Classification of strip steel surface defects based on data augmentation combined with MobileNet
Feng, X., Gao, X., & Luo, L. (2022) · Chinese Control Conference (CCC) · doi:10.23919/ccc55666.2022.9902206 · Cited by 6
Self-citationLu, K., Wang, W., Feng, X., Zhou, Y., Chen, Z., Zhao, Y., & Wang, B. (2023) · ISIJ International · doi:10.2355/isijinternational.isijint-2023-182 · Cited by 6
Self-citationSurface Defect Identification of Strip Steel Using ViT‐RepVGG
Wang, Z., Long, M., Sun, P., et al. (2024) · steel research international · doi:10.1002/srin.202400569 · Cited by 5
Nergiz, M. E. (2021) · International Conference on Computer Science and Engineering (UBMK) · doi:10.1109/ubmk52708.2021.9558941 · Cited by 5
Yan, H., Zhang, Z., Peng, T., et al. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.114606 · Cited by 4
Improving Image Representation for Surface Defect Recognition with Small Data
Phuong, T. T., Tin, D. D., & Trang, L. H. (2024) · Journal of Advances in Information Technology · doi:10.12720/jait.15.5.572-579 · Cited by 5
“In 2021, Feng et al. [24] proposed a hot rolled steel strip defect dataset called Xsteel Surface Defect Dataset (X-SDD) with 1360 images of seven typical defect types.”
Foreign object detection in the inspection of cloud server center using separable self-attention
Jiang, Y., Li, Z., Zhao, B., Zhang, X., & Dong, X. (2025) · Intelligent Service Robotics · doi:10.1007/s11370-024-00580-z · Cited by 4
“The results 1–2 in Table 6 were obtained through self-experimentation, while 3 were obtained from [36], 4-5 from [38], 6 from[33], and 7 from [34].”
Advancing Small Defect Recognition in PV Modules with YOLO-FAD and Dynamic Convolution
Li, L., Xie, G., Wang, Y., Yun, W., Wang, J.-A., & Zhao, Z. (2025) · Computers · doi:10.3390/computers14120518 · Cited by 7
Hussain, T., & Seok, J. (2024) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2024.056621 · Cited by 6
Research on surface defect detection model of steel strip based on MFFA‐YOLOv5
Chen, H., Qiu, J., Gao, D., Qian, L., & Li, X. (2024) · IET Image Processing · doi:10.1049/ipr2.13086 · Cited by 4
A Review and Benchmark on State-of-The-Art Steel Defects DetectionPreprint
Chazhoor, A. A. P., Ho, E. S. L., Woo, W. L., & Gao, B. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4121951 · Cited by 5
Wen, X., Zhao, W., Yu, Z., Zhao, J., & Song, K. (2023) · Coatings · doi:10.3390/coatings13071171 · Cited by 4
S 2 -AMNet: A lightweight Spatial–Spectral Adaptive Modulation Network for surface defect detection
Bao, J., Zhang, C., Bao, L., & Zhang, J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112778 · Cited by 6
Wei, J., Chen, X., Liu, Y., & Feng, X. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.130939 · Cited by 9
Self-citationSupervision dropout: guidance learning in deep neural network
Zeng, L., Zhang, H., Li, Y., Li, M., & Wang, S. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-14274-0 · Cited by 3
“With the development of information technology, deep neural networks(DNNs) [2, 7, 32] have made great progresses in multiple fields, such as image classification [9, 17, 19], target detection [13, 45] and semantic segmentation [42].”
MethodResearch on strip surface defect detection based on improved YOLOv5 algorithm
Lv, S., Tao, C., Hao, Z., Ni, H., Hou, Z., Li, X., Gu, H., Shi, W., & Chen, L. (2024) · Ironmaking & Steelmaking Processes Products and Applications · doi:10.1177/03019233241260922 · Cited by 6
“X-SDD surface defect image dataset of hot-rolled strip steel 26 was used to classify the surface defects of strip steel, which included 7 types, with a total of 1360 defect images, the size of the images are 128 × 128 pixels, and the format is 3-channel JPG, as shown in Figure 1.”
Current Trends on Deep Learning Techniques Applied in Iron and Steel Making Field: A Review
Tsutsui, K., Namba, T., Kihara, K., Hirata, J., Matsuo, S., & Ito, K. (2022) · 鐵と鋼 : 日本鐡鋼協會々誌 · doi:10.2355/tetsutohagane.tetsu-2022-098 · Cited by 5
Mobile Vision Transformer for Surface Defect Classification from A Tiny Dataset
Sari, G. I. P., Pao, H.-K., Pribadi, R. C. H., & Iqbal, M. A. (2023) · International Conference on Information & Communication Technology and System (ICTS) · doi:10.1109/icts58770.2023.10330837 · Cited by 2
“Recently, Feng, et al. [4] launched a new benchmark dataset for SDC on HRSS, which has more defect types on HRSS compared to the common related dataset.”
BackgroundMethodInfluentialWang, X., Xian, W., Li, J., et al. (2025) · Complex & Intelligent Systems · doi:10.1007/s40747-025-02131-0 · Cited by 2
Zhang, H., Liu, H., Ma, W., Zheng, C., Zhang, T., Guo, R., Liang, L., & Liu, Q. (2026) · Measurement · doi:10.1016/j.measurement.2026.120375 · Cited by 6
Wang, X., Li, Y., Gong, Y., Liu, M., & Luo, K. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02774-3 · Cited by 2
A Review of Deep Learning Methods for Metal Surface Defect Detection
Qin, G., Liu, C., Li, H., & Xu, K. (2026) · steel research international · doi:10.1002/srin.202501060 · Cited by 4
YOLOv5s-DNF: A lighter and real-time method for detecting surface defects in steel
Ding, H., & Xia, B. (2023) · International Conference on Computer Vision, Image and Deep Learning (CVIDL) · doi:10.1109/cvidl58838.2023.10166850 · Cited by 2
Hot-Rolled Steel Strip Defect Classification Based on ResNet34 Model
Lu, W., & Yang, L. (2023) · International Conference on Machine Learning, Cloud Computing and Intelligent Mining (MLCCIM) · doi:10.1109/mlccim60412.2023.00025 · Cited by 2
ScissionLite: Accelerating Distributed Deep Learning With Lightweight Data Compression for IIoT
Ahn, H., Lee, M., Seong, S., Na, G.-J., Chun, I., Varghese, B., & Hong, C.-H. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3413340 · Cited by 5
“We also employed a subset of ImageNet [10] called ILSVRC and the X-SDD [11] as image databases.”
BackgroundMethodMetal Structural Defect Detection Based-On Deep Learning and Grad-Cam
Mehadjbia, A., & Slaoui-Hasnaoui, F. (2024) · International Conference on Circuit, Systems and Communication (ICCSC) · doi:10.1109/iccsc62074.2024.10617066 · Cited by 2
“Feng et al. [21] (2021), The work consists of applying the RepVGG+SA approach by integrating a spatial attention mechanism for annotating faults in the X-SDD dataset.”
Method
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
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.