Deep Open-Set Recognition for Silicon Wafer Production Monitoring

TL;DR

This paper introduces a deep learning approach using Submanifold Sparse Convolutional Networks for open-set recognition of wafer defect maps, enabling accurate classification of known defect patterns and detection of novel failures in semiconductor manufacturing.

Contribution

It presents a novel pipeline combining sparse convolutional networks and Gaussian Mixture Model-based outlier detection for wafer defect monitoring, improving accuracy and novelty detection over existing methods.

Findings

Superior classification of known defect patterns.

Enhanced detection of novel defect patterns.

Outperforms traditional CNNs and state-of-the-art open-set methods.

Abstract

The chips contained in any electronic device are manufactured over circular silicon wafers, which are monitored by inspection machines at different production stages. Inspection machines detect and locate any defect within the wafer and return a Wafer Defect Map (WDM), i.e., a list of the coordinates where defects lie, which can be considered a huge, sparse, and binary image. In normal conditions, wafers exhibit a small number of randomly distributed defects, while defects grouped in specific patterns might indicate known or novel categories of failures in the production line. Needless to say, a primary concern of semiconductor industries is to identify these patterns and intervene as soon as possible to restore normal production conditions. Here we address WDM monitoring as an open-set recognition problem to accurately classify WDM in known categories and promptly detect novel patterns. In particular, we propose a comprehensive pipeline for wafer monitoring based on a Submanifold Sparse Convolutional Network, a deep architecture designed to process sparse data at an arbitrary resolution, which is trained on the known classes. To detect novelties, we define an outlier detector based on a Gaussian Mixture Model fitted on the latent representation of the classifier. Our experiments on a real dataset of WDMs show that directly processing full-resolution WDMs by Submanifold Sparse Convolutions yields superior classification performance on known classes than traditional Convolutional Neural Networks, which require a preliminary binning to reduce the size of the binary images representing WDMs. Moreover, our solution outperforms state-of-the-art open-set recognition solutions in detecting novelties.