Wafer-View Defect-Pattern-Prominent GDBN Method Using MetaFormer Variant

EasyChair Preprint 15192, version 2

Abstract

Good-Die-in-Bad-Neighborhood (GDBN) is a technique employed to identify chips that pass initial tests but may have defects. Previous research used neural networks and expanded observation windows but ignored the impact of isolated dice. This paper improves wafer pattern information through denoising and creates a lightweight model. It also reduces training time by annotating multiple dice simultaneously. Experiments on real-world datasets show the model effectively captures more Test Escapes, reducing Defective Parts Per Million (DPPM) and improving return merchandise authorization gains.

Keyphrases: Defective parts per million (DPPM), Geographical part average testing (GPAT), Good-die-in-bad-neighborhood (GDBN), Latent defect, neural network

@booklet{EasyChair:15192,
  author    = {Shu-Wen Li and Chia-Heng Yen and Shuo-Wen Chang and Ying-Hua Chu and Kai-Chiang Wu and Chia-Tso Chao},
  title     = {Wafer-View Defect-Pattern-Prominent GDBN Method Using MetaFormer Variant},
  howpublished = {EasyChair Preprint 15192},
  year      = {EasyChair, 2024}}