Deep convolutional neural networks (CNNs) have been widely used in surface defect detection. However, no CNN architecture is suitable for all detection tasks and designing effective task-specific architectures requires considerable effort. The neural architecture search (NAS) technology makes it possible to automatically generate adaptive data-driven networks. Here, we propose a new method called NAS-ASDet to adaptively design network for surface defect detection. First, a refined and industry-appropriate search space that can adaptively adjust the feature distribution is designed, which consists of repeatedly stacked basic novel cells with searchable attention operations. Then, a progressive search strategy with a deep supervision mechanism is used to explore the search space faster and better. This method can design high-performance and lightweight defect detection networks with data scarcity in industrial scenarios. The experimental results on four datasets demonstrate that the proposed method achieves superior performance and a relatively lighter model size compared to other competitive methods, including both manual and NAS-based approaches.

中文翻译：

---

NAS-ASDet：一种使用神经架构搜索的表面缺陷检测网络的自适应设计方法

深度卷积神经网络（CNN）已广泛应用于表面缺陷检测。然而，没有任何 CNN 架构适合所有检测任务，设计有效的特定任务架构需要付出相当大的努力。神经架构搜索（NAS）技术使得自动生成自适应数据驱动网络成为可能。在这里，我们提出了一种称为 NAS-ASDet 的新方法来自适应设计表面缺陷检测网络。首先，设计了一个可以自适应调整特征分布的精细且适合行业的搜索空间，该空间由重复堆叠的具有可搜索注意操作的基本新颖单元组成。然后，使用具有深度监督机制的渐进搜索策略来更快更好地探索搜索空间。该方法可以在工业场景下设计数据稀缺的高性能、轻量级缺陷检测网络。四个数据集上的实验结果表明，与其他竞争方法（包括手动方法和基于 NAS 的方法）相比，所提出的方法具有卓越的性能和相对较小的模型大小。