[1]ZHANG Ji,WANG Dingbang,CAO Jingang,et al.Improvement of YOLOv8 for lightweight steel surface defect detection[J].CAAI Transactions on Intelligent Systems,2026,21(2):375-388.[doi:10.11992/tis.202504018]
Copy

Improvement of YOLOv8 for lightweight steel surface defect detection

CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume: 21 Number of periods: 2026 2 Page number: 375-388 Column: 学术论文—机器学习 Public date: 2026-05-16
Title:
Improvement of YOLOv8 for lightweight steel surface defect detection
Author(s):
ZHANG Ji1; 2;  WANG Dingbang1;  CAO Jingang1; 2;  YANG Liran1; 2
1. Department of Computer Science, North China Electric Power University, Baoding 071003, China;
2. Engineering Research Center of intelligent Computing for Complex Energy Systems Ministry of Education, North China Electric Power University, Baoding 071003, China
Keywords:
lightweight network; defect detection; YOLOv8n; multiscale feature fusion; feature extraction; spatial pyramid; object detection; WIoU
CLC:
TP391.4；TG115
DOI:
10.11992/tis.202504018
Abstract:
Surface defects of steel plates still face significant issues of missed and false detections, as well as difficulties in deployment on edge devices. To address these problems, a lightweight steel surface defect detection algorithm based on YOLOv8 is proposed. First, a Partial Convolution Gated Linear Unit (PGBN) module is designed to replace the BottleNeck module, performing convolution operations only on part of the channels to reduce the model’s parameters. Next, the Spatial Pyramid Pooling module is improved by using convolutions with different dilation rates to enhance the extraction of fine-grained features. Then, GLFPN is proposed by combining the Global-to-Local Spatial Aggregation (GLSA) module with the improved BiFPN structure. Its weighted fusion can more effectively retain small sample features, thereby improving the model’s accuracy. After that, a more lightweight detection head is designed to further reduce the model’s parameters and computational load. Finally, the WIoU loss function is used to replace the original CIoU. Experimental results show that the improved model achieves an mAP50 of 79.6% on the NEU-DET dataset, a 4.2 percent improvement over YOLOv8n, while the model parameters and computational load are only 1.43×106 and 4.7×109, respectively, representing a 53.3% and 41.9% reduction compared to YOLOv8n. This makes the model more accurate while being more suitable for deployment on edge devices.
References:
[1] WANG Ling, LIU Xinbo, MA Juntao, et al. Real-time steel surface defect detection with improved multi-scale YOLO-v5[J]. Processes, 2023, 11(5): 1357.
[2] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus: IEEE, 2014: 580-587.
[3] GIRSHICK R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision. Santiago: IEEE, 2015: 1440-1448.
[4] REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//IEEE Transactions on Pattern Analysis and Machine Intelligence. [S. l. ]: IEEE, 2017: 1137-1149.
[5] CAI Zhaowei, VASCONCELOS N. Cascade R-CNN: delving into high quality object detection[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 6154-6162.
[6] PANG Jiangmiao, CHEN Kai, SHI Jianping, et al. Libra R-CNN: towards balanced learning for object detection[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 821-830.
[7] 陈远露, 王亮. 基于Transformer与FasterRCNN的多模态特征提取与融合[J]. 信息技术与信息化, 2024(5): 111-114. CHEN Yuanlu, WANG Liang. Multi-modal feature extraction and fusion based on Transformer and FasterRCNN[J]. Information technology and informatization, 2024(5): 111-114.
[8] SUN Peize, ZHANG Rufeng, JIANG Yi, et al. Sparse R-CNN: end-to-end object detection with learnable proposals[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 14449-14458.
[9] 邓慧, 曾磊. 基于改进Faster R-CNN的热轧带钢表面缺陷检测[J]. 控制工程, 2024, 31(4): 752-759. DENG Hui, ZENG Lei. Surface defect detection of hot-rolled strip steel based on improved faster R-CNN[J]. Control engineering of China, 2024, 31(4): 752-759.
[10] LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[C]//Computer Vision–ECCV 2016. Cham: Springer International Publishing, 2016: 21-37.
[11] HUSSAIN M. YOLO-v1 to YOLO-v8, the rise of YOLO and its complementary nature toward digital manufacturing and industrial defect detection[J]. Machines, 2023, 11(7): 677.
[12] WANG Ao, CHEN Hui, LIU Lihao, et al. Yolov10: real-time end-to-end object detection[J]. Advances in neural information processing systems, 2024, 37: 107984-108011.
[13] KHANAM R, HUSSAIN M. YOLOv11: an overview of the key architectural enhancements[EB/OL]. (2024-10-23)[2025-04-23]. https://arxiv.org/abs/2410.17725.
[14] 李刚, 邵瑞, 周鸣乐, 等. 基于注意力的轻量级工业产品缺陷检测网络[J]. 计算机工程, 2023, 49(11): 275-283. LI Gang, SHAO Rui, ZHOU Mingle, et al. Lightweight industrial products defect detection network based on attention[J]. Computer engineering, 2023, 49(11): 275-283.
[15] 忻迪晔, 严怀成. 基于GS-YOLO模型的带钢表面缺陷检测[J]. 计算机应用, 2024, 44(S2): 302-308. XIN Diye, YAN Huaicheng. Surface defect detection of strip steel based on GS-YOLO model[J]. Journal of computer applications, 2024, 44(S2): 302-308.
[16] 敖思铭, 周诗洋, 杨智颖, 等. 基于KAS-YOLO的钢板表面缺陷检测[J]. 组合机床与自动化加工技术, 2024(8): 168-174. AO Siming, ZHOU Shiyang, YANG Zhiying, et al. Surface defect detection of steel plate based on KAS-YOLO[J]. Modular machine tool & automatic manufacturing technique, 2024(8): 168-174.
[17] 侯玥, 王开宇, 金顺福. 一种基于YOLOv5的小样本目标检测模型[J]. 燕山大学学报, 2023, 47(1): 64-72. HOU Yue, WANG Kaiyu, JIN Shunfu. A few-shot object detection model based on YOLOv5[J]. Journal of Yanshan University, 2023, 47(1): 64-72.
[18] 张上, 许欢, 张岳. 轻量级锻件表面裂纹检测算法[J]. 电子测量技术, 2024, 47(11): 123-130 ZHANG Shang, XU Huan, ZHANG Yue. Lightweight forged part surface crack detection algorithm[J]. Electronic measurement technology, 2024, 47(11): 123-130
[19] CHEN Jierun, KAO S H, HE Hao, et al. Run, don’t walk: chasing higher FLOPS for faster neural networks[C]//2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Vancouver: IEEE, 2023: 12021-12031.
[20] SHI Dai. TransNeXt: robust foveal visual perception for vision Transformers[C]//2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2024: 17773-17783.
[21] DAUPHIN Y N, FAN A, AULI M, et al. Language modeling with gated convolutional networks[C]//International Conference on Machine Learning. Sydney: PMLR, 2017: 933-941.
[22] TAN Mingxing, PANG Ruoming, LE Q V. EfficientDet: scalable and efficient object detection[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020: 10778-10787.
[23] TANG Feilong, XU Zhongxing, HUANG Qiming, et al. DuAT: dual-aggregation Transformer network for medical image segmentation[C]//Chinese Conference on Pattern Recognition and Computer Vision. Singapore: Springer Nature Singapore, 2023: 343-356.
[24] TIAN Zhi, SHEN Chunhua, CHEN Hao, et al. FCOS: a simple and strong anchor-free object detector[J]. IEEE transactions on pattern analysis and machine intelligence, 2022, 44(4): 1922-1933.
[25] YEUNG C C, LAM K M. Efficient fused-attention model for steel surface defect detection[J]. IEEE transactions on instrumentation and measurement, 2022, 71: 2510011.
[26] WANG Xing, ZHUANG Kaiyu. An improved YOLOX method for surface defect detection of steel strips[C]//2023 IEEE 3rd International Conference on Power, Electronics and Computer Applications. Shenyang: IEEE, 2023: 152-157.
[27] 梁礼明, 陈康泉, 陈林俊, 等. 改进轻量化的FCM-YOLOv8n钢材表面缺陷检测[J]. 光电工程, 2025, 52(2): 117-129. LIANG Liming, CHEN Kangquan, CHEN Linjun, et al. Improving the lightweight FCM-YOLOv8n for steel surface defect detection[J]. Opto-electronic engineering, 2025, 52(2): 117-129.
[28] 李相垚, 侯红玲, 杨澳, 等. 面向钢材表面缺陷检测的DCS-YOLOv8算法研究[J/OL]. 机械科学与技术, 2024: 1-10. (2024-10-10). https://link.cnki.net/doi/10.13433/j.cnki.1003-8728.20240128. LI Xiangyao, HOU Hongling, YANG Ao, et al. Research on DCS-YOLOv8 algorithm for steel surface defect detection[J/OL]. Mechanical science and technology for aerospace engineering, 2024: 1-10. (2024-10-10). https://link.cnki.net/doi/10.13433/j.cnki.1003-8728.20240128.
[29] 赵曙光, 易文, 陆小辰. 基于YOLOv7-Tiny的轻量化钢材表面缺陷检测方法[J]. 东华大学学报(自然科学版), 2025, 51(4): 194-202. ZHAO Shuguang, YI Wen, LU Xiaochen. Lightweight steel surface defect detection method based on YOLOv7-Tiny[J]. Journal of Donghua University (natural science), 2025, 51(4): 194-202.
[30] HU Jie, SHEN Li, SUN Gang. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018: 7132-7141.
[31] WOO S, PARk J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision. Munich: Springer, 2018: 3-19.
[32] HOU Qibin, ZHOU Daquan, FENG Jiashi. Coordinate attention for efficient mobile network design[C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Nashville: IEEE, 2021: 13708-13717.
[33] OUYANG Daliang, HE Su, ZHANG Guozhong, et al. Efficient multi-scale attention module with cross-spatial learning[C]//2023 IEEE International Conference on Acoustics, Speech and Signal Processing. Rhodes Island: IEEE, 2023: 1-5.
Similar References:

Memo

-

Last Update: 1900-01-01

Copyright © CAAI Transactions on Intelligent Systems