NAS-ASDet: An Adaptive Design Method for Surface Defect Detection Network using Neural Architecture Search
This work addresses the challenge of efficient and effective network design for surface defect detection in industrial settings, where data scarcity is common, representing an incremental improvement in applying NAS to a specific domain.
The authors tackled the problem of designing task-specific convolutional neural networks for surface defect detection by proposing NAS-ASDet, a method using neural architecture search to automatically generate adaptive networks, achieving superior performance and lighter models on four datasets compared to manual and NAS-based approaches.
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 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.