A NOVEL GAN-BASED DATA AUGMENTATION ALGORITHM FOR SEMICONDUCTOR DEFECT INSPECTION

被引：1

作者：

Liu, Yang ^{[1
]}

Guan, Yuanjun ^{[1
]}

Han, Tianyan ^{[2
]}

Ma, Can ^{[1
]}

Wang, Jiayi ^{[1
]}

Wang, Tao ^{[1
]}

Yi, Qianchuan ^{[1
]}

Hu, Lilei ^{[1
,2
]}

机构：

[1] Shanghai Univ, Sch Microelect, Shanghai 200444, Peoples R China

[2] Shanghai Ind Technol Res Inst, Shanghai, Peoples R China

来源：

CONFERENCE OF SCIENCE & TECHNOLOGY FOR INTEGRATED CIRCUITS, 2024 CSTIC | 2024年

基金：

中国国家自然科学基金;

关键词：

Generative Adversarial Networks; semiconductor defect inspection; residual networks;

D O I：

10.1109/CSTIC61820.2024.10531884

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

A deep learning solution is proposed for the problem of object inspection in semiconductor images. Supervised learning method approaches require large annotated semiconductor datasets, which are often difficult to obtain. Therefore, we develop a new deep convolutional generative adversarial network (DCGAN)) to generate simulated data. Real image data and generated image data are used to train the residual network (ResNet) defect inspection network. Compared to training with the original dataset, using the synthetic dataset resulted in a 3.12% improvement in the accuracy of local defect detection. The total defect inspection accuracy also improves from 93.75% to 95.31%.

引用

页数：3

共 4 条

[1] Deep Residual Learning for Image Recognition [J].

He, Kaiming ;

Zhang, Xiangyu ;

Ren, Shaoqing ;

Sun, Jian .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778

[2] Generative adversarial networks-based super-resolution algorithm enables high signal-to-noise ratio spatial heterodyne Raman spectra [J].

Hu, Lilei ;

Shen, Jingxuan ;

Chen, Zhu ;

Zhang, Yichen ;

Chen, Chang .

JOURNAL OF RAMAN SPECTROSCOPY, 2023, 54 (12) :1490-1501

[3]

Radford A, 2016, Arxiv, DOI arXiv:1511.06434

[4] A Deep Convolutional Neural Network for Wafer Defect Identification on an Imbalanced Dataset in Semiconductor Manufacturing Processes [J].

Saqlain, Muhammad ;

Abbas, Qasim ;

Lee, Jong Yun .

IEEE TRANSACTIONS ON SEMICONDUCTOR MANUFACTURING, 2020, 33 (03) :436-444

← 1 →