A Suspected Defect Screening-Guided Lightweight Network for Few-Shot Aviation Steel Tube Surface Defect Segmentation

Internal surface defect segmentation is an important technology of quality detection in the production of aviation steel tubes (ASTs). However, there are still some challenges, such as the imbalance of nondefect samples and defect samples, the comprehensive sparsity of defect category and defect sample quantity, and the constraint between hardware computing power and model accuracy. In this work, a lightweight suspected defect screening network (SDSNet) based on transfer learning is proposed to filter out redundant nondefect samples. Besides, to overcome the comprehensive sparsity of AST defect samples, we introduce a granularity-transfer few-shot defect segmentation (FSDS) based on meta-learning. Subsequently, we propose a lightweight feature-aware segmentation network (FASNet) further to segment the suspected defect sample pixel-wise. Specifically, a defect-aware module (DAM) is employed to activate spatial and channel responses of defect regions, and a lightweight multiscale aggregation decoder (MAD) is used to capture context information at different feature scales. In addition, to evaluate the effectiveness of the proposed pipeline and overcome the practical challenge of AST defect segmentation, a dedicated database is constructed. Our pipeline achieves a 98.6% precision for suspected defect screening and 66.94% MIoU for defect segmentation. Extensive experiments evaluate the feasibility of deploying our pipeline on the edge computing equipment based on the NPU platform with low computational cost in industrial production.