Wafer defect pattern recognition based on differentiable architecture search with dual attention module

Abstract

Abstract Wafer defect pattern recognition is a crucial process for ensuring chip production quality. Due to the complexity of wafer production processes, wafers often contain multiple defect patterns simultaneously, making it challenging for existing deep learning algorithms designed for single defect patterns to achieve optimal performance. To address this issue, this paper proposes a dual attention integrated differentiable architecture search (DA-DARTS), which can automatically search for suitable neural network architectures, significantly simplifying the architecture design process. Furthermore, the integration of DA greatly enhances the efficiency of the architecture search. We validated our proposed method on the MixedWM38 dataset, and experimental results indicate that the DA-DARTS method achieves higher pattern recognition accuracy under mixed defect patterns compared to baseline methods, maintaining performance stability even on imbalanced datasets.