One-Class Classification for Wafer Map using Adversarial Autoencoder with DSVDD Prior

TL;DR

This paper introduces a novel one-class classification approach for wafer map defect detection using an adversarial autoencoder combined with a DSVDD prior, addressing the challenge of imbalanced defect data in semiconductor manufacturing.

Contribution

The paper proposes a new one-class classification method that integrates an adversarial autoencoder with a DSVDD prior, improving defect detection without requiring extensive labeled data.

Findings

The proposed method outperforms DSVDD and AAE in F1 score on wafer map data.

It effectively detects defects in imbalanced datasets.

The approach reduces the need for labeled defect data in quality assurance.

Abstract

Recently, semiconductors' demand has exploded in virtual reality, smartphones, wearable devices, the internet of things, robotics, and automobiles. Semiconductor manufacturers want to make semiconductors with high yields. To do this, manufacturers conduct many quality assurance activities. Wafer map pattern classification is a typical way of quality assurance. The defect pattern on the wafer map can tell us which process has a problem. Most of the existing wafer map classification methods are based on supervised methods. The supervised methods tend to have high performance, but they require extensive labor and expert knowledge to produce labeled datasets with a balanced distribution in mind. In the semiconductor manufacturing process, it is challenging to get defect data with balanced distribution. In this paper, we propose a one-class classification method using an Adversarial Autoencoder (AAE) with Deep Support Vector Data Description (DSVDD) prior, which generates random vectors within the hypersphere of DSVDD. We use the WM-811k dataset, which consists of a real-world wafer map. We compare the F1 score performance of our model with DSVDD and AAE.