Enhanced Defect Detection Network: Leveraging Large Kernel and Dynamic Task Interaction for Precise Prediction

The surface quality of steel directly affects its performance and durability in industrial production. However, traditional deep learning technology struggles to balance performance and efficiency in detecting intricate steel surface flaws. This paper presents an enhanced defect detection network (EDDN) for real-time steel surface defect detection. First, we design a large kernel feature enrichment module (LFEM) to fuse the feature layers with rich detail information, while using continuous large kernel convolution to capture multi-scale features. Notably, a dynamic selection mechanism that adaptively captures significant spatial features on the basis of global information. This design addresses the problem of tiny and complicated target detection failures and significantly increases detection accuracy. In addition, we propose a dynamic task interaction detection head (DT-Head) that balances the detection by enabling the dynamic interaction between the localization and classification tasks. This interaction mechanism allows the two tasks to collaborate better for a more accurate prediction. Finally, extensive experiments on NEU-DET and GC10-DET show that EDDN improves mAP@50 accuracy by 2.9% and 4.6%, achieving detection speeds of 79 and 72 frames per second (FPS), respectively, outperforming current mainstream algorithms in terms of accuracy and efficiency.