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.
@article{arxiv.2311.10952,
title = {NAS-ASDet: An Adaptive Design Method for Surface Defect Detection Network using Neural Architecture Search},
author = {Zhenrong Wang and Bin Li and Weifeng Li and Shuanlong Niu and Wang Miao and Tongzhi Niu},
journal= {arXiv preprint arXiv:2311.10952},
year = {2023}
}