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

EasyChair Preprint 15192, version 1

Abstract

We utilized a denoising technique, a flexible input-size model, and a new training strategy to detect latent defects based on neighboring information. This approach reduced DPPM (defective parts per million) by 24%

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}}