Multi-scale contextual modeling and fine-grained adaptive fusion for real-time surface defect detection
- 1School of Intelligent Manufacturing and Robotics, Anqing Normal University
- 2School of Artificial Intelligence and Computing, Anqing Normal University
Abstract
Surface defect detection in steel strips requires both accurate recognition and efficient inference under complex industrial backgrounds. Existing methods still encounter difficulties in modeling scale-varied defects, preserving fine-grained defect cues, and aligning multi-level features efficiently. To address these issues, we propose CDF-YOLO, a real-time detection framework that integrates multi-scale contextual modeling and fine-grained adaptive fusion on the YOLOv12 baseline. Specifically, a Dilated Context Pyramid Bottleneck (C2f_DCPB) is introduced to enhance contextual representation through parallel dilated branches; a Fine-grained Adaptive Fusion module (FAN_Block) is embedded into the high-resolution path to strengthen local texture and structural-detail representation; and DySample is adopted to improve content-adaptive upsampling for multi-scale feature fusion. Experiments on the NEU-DET dataset show that CDF-YOLO achieves an mAP50 of 95.4% and 101.3 FPS under the adopted test protocol, while cross-dataset evaluation on DeepPCB further indicates improved generalization performance. These results suggest that CDF-YOLO provides a favorable accuracy-efficiency trade-off on public industrial defect datasets. Nevertheless, validation on larger-scale production-line data and further optimization for edge deployment remain necessary for practical industrial application.
Related
- CFT-Triplet: integrating contextual, frequency and textural features for fine-grained pulmonary fissure detection
- Spatially-adaptive dynamic dictionary learning for fine-grained remote sensing image segmentation
- Time-step level sleep apnea detection using LSTM with adaptive thresholding in polysomnography
- Customizable bead-based platform for EV surface protein immunocapture and detection in plasma
- Precise modeling of task-related sensorimotor activation based on simultaneous surface electromyography
BibTeX
@article{dong2026multiscale,
title = {{Multi-scale contextual modeling and fine-grained adaptive fusion for real-time surface defect detection}},
author = {Jiadong Dong and Qinghu Guo and Feihu Sang and Chunxiang Zheng},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-63696-5},
url = {https://doi.org/10.1038/s41598-026-63696-5},
note = {CC BY},
}
RIS
TY - JOUR
TI - Multi-scale contextual modeling and fine-grained adaptive fusion for real-time surface defect detection
AU - Jiadong Dong
AU - Qinghu Guo
AU - Feihu Sang
AU - Chunxiang Zheng
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-63696-5
UR - https://doi.org/10.1038/s41598-026-63696-5
AB - Surface defect detection in steel strips requires both accurate recognition and efficient inference under complex industrial backgrounds. Existing methods still encounter difficulties in modeling scale-varied defects, preserving fine-grained defect cues, and aligning multi-level features efficiently. To address these issues, we propose CDF-YOLO, a real-time detection framework that integrates multi-scale contextual modeling and fine-grained adaptive fusion on the YOLOv12 baseline. Specifically, a Dilated Context Pyramid Bottleneck (C2f_DCPB) is introduced to enhance contextual representation through parallel dilated branches; a Fine-grained Adaptive Fusion module (FAN_Block) is embedded into the high-resolution path to strengthen local texture and structural-detail representation; and DySample is adopted to improve content-adaptive upsampling for multi-scale feature fusion. Experiments on the NEU-DET dataset show that CDF-YOLO achieves an mAP50 of 95.4% and 101.3 FPS under the adopted test protocol, while cross-dataset evaluation on DeepPCB further indicates improved generalization performance. These results suggest that CDF-YOLO provides a favorable accuracy-efficiency trade-off on public industrial defect datasets. Nevertheless, validation on larger-scale production-line data and further optimization for edge deployment remain necessary for practical industrial application.
SN - 2045-2322
ER -