Deep open-set recognition for silicon wafer production monitoring
作者：
Highlights：
• A novel solution to monitor the production of silicon wafers by Deep Learning models.
• A crucial problem for semiconductor industry, challenging due to the huge input size.
• We accurately address wafer monitoring as an open-set recognition problem.
• Our network can process huge inputs as lists of defects, without loss of information.
• We employ latent representation of our deep model to identify novel patterns.
摘要
•A novel solution to monitor the production of silicon wafers by Deep Learning models.•A crucial problem for semiconductor industry, challenging due to the huge input size.•We accurately address wafer monitoring as an open-set recognition problem.•Our network can process huge inputs as lists of defects, without loss of information.•We employ latent representation of our deep model to identify novel patterns.
论文关键词：Pattern classification,Open-set recognition,Sparse convolutions,Quality inspection,Wafer monitoring
论文评审过程：Received 22 January 2021, Revised 15 October 2021, Accepted 4 December 2021, Available online 7 December 2021, Version of Record 21 December 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108488
