A Novel Fusion Attention-Based Lightweight Model for Pipeline Weld Multiscale Defect Detection

Weld defect detection is critical for maintaining the safe operation of natural gas pipelines. While computer vision-based approaches have emerged as a promising research focus, existing deep learning models inevitably face the problem of limited detection accuracy in multiscale welding defect detection, especially in recognizing tiny welding defects. To overcome the above challenges, this article proposes a novel DySample-guided lightweight feature aggregation fusion network (DyLFA-Net) for weld defect detection in natural gas pipelines, aiming to improve detection accuracy and computational efficiency while preserving a compact architectural design. The DyLFA-Net model consists of two key components. 1) The IB-SCSA module at the P5 layer, which enhances multiscale semantic extraction via spatial-channel attention. The IB module enhances feature expressiveness through channel expansion and depthwise convolution, supplying the SCSA mechanism with semantically enriched input features. 2) A high-resolution detection head at the P2 layer to improve tiny defect recognition. Experiments show that the proposed model achieves an mAP@0.5 of 89.9%, outperforming mainstream detectors. Additionally, with just 1.31 M parameters and 6.6 GFLOPs, the proposed model offers high accuracy and low complexity, enabling real-time deployment on resource-limited edge devices.