STMA-Net: A Spatial Transformation-Based Multi-Scale Attention Network for Complex Defect Detection with X-ray Images

In the welding process of long-distance pipelines, cracks pose significant risks and can cause severe damages. Intelligent detection of hazardous defects in pipeline welds, with a focus on complex crack features with different shapes and scales, is a necessary but challenging task. Current deep learning-based visual detection models exhibit weak generalization and transfer capabilities when it comes to complex defect features. To address these challenges, this paper proposes a spatial transformation-based multi-scale attention network (STMA-Net) for weld defect detection with multi-scale and shape-variant features in X-ray images. First, a novel spatial transformation attention network (STAN) is designed to capture the complex deformation features, which enhances the generalization ability of the feature extraction network. Then, in order to better utilize the discriminative features, a multi-level attention feature fusion network (MAFFN) is designed to improve the prediction accuracy of multi-scale defects. Furthermore, a multi-level deep supervision is proposed to better update network parameters and enhance the inference ability of multi-level detection heads. Finally, three types of X-ray weld crack datasets in the real world are collected to guide a series of experiments and analyses. The results show that the generalization and transfer capabilities of the proposed method outperforms other detectors in the detection task of cracks and other defects (AP increased by 6.5%).