小样本条件下的带钢表面缺陷检测

针对工业场景下带钢表面缺陷样本少、缺陷尺寸大小不一等问题, 提出一种适用于小样本条件下的带钢表面缺陷检测网络. 首先, 算法以YOLOv5s框架为基础, 设计一种融合注意力机制的多尺度路径聚合网络作为模型的颈部, 增强模型对缺陷目标的多尺度预测能力; 其次, 提出一种自适应解耦检测结构, 缓解小样本情况下分类和定位任务之间的矛盾; 最后, 提出一种融合Wasserstein距离的边界框回归损失函数, 提升模型对小目标缺陷的检测精度. 实验表明, 在构建的小样本带钢表面缺陷数据集上, 本文模型的检测性能优于其他小样本检测模型, 更适用于工业环境下的小样本缺陷检测任务.

Surface Defect Detection of Strip Steel with Few Shots

To address the problems of few shots and varying sizes in the surface defects on steel strips in industrial scenarios, this study proposes a detection network for surface defects on steel strips readily applicable to few-shot situations. Specifically, the algorithm is based on the you only look once version 5 small (YOLOv5s) framework and a multi-scale path aggregation network with an attention mechanism is designed to serve as the neck of the model and thereby enhance the ability of the model to predict the defect objects on multiple scales. Then, an adaptive coord-decoupled head is proposed to alleviate the contradiction among classification and positioning tasks in few-shot scenarios. Finally, a bounding box regression loss function fused with the Wasserstein distance is presented to improve the accuracy of the model in detecting small defect objects. Experiments show that the proposed model outperforms other few-shot object detection models on the few-shot dataset of surface defects on steel strips, indicating that it is more suitable for few-shot defect detection tasks in industrial environments.