Work

SePArate: Segmenting Patterns from Defects in Wafer Manufacturing Using Weak Supervision

Year: 2026

Type: preprint

Abstract: In semiconductor manufacturing, defect analysis is essential, but manual inspection cannot scale. However, existing automated inspection methods remain insufficient for root-cause analysis and process optimization. To this end, we present SePArate, a weakly supervised wafer defect segmentation method. SePArate enables pixel-level separation of patterns by leveraging only image-level annotations. It consists of a three-phase training: encoder pretraining, knowledge transfer to learn spatial cues, and training on synthetic mixed-defect data for accurate segmentation. Experiments demonstrate that SePArate outperforms the baselines.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2608.30410

Authors: Kwon, Dain, Shin, Changmin, Park, Sunjong, Choi, Kanghyun, Lee, Hyeyoon, Jang, Jaewon, Choi, Minseok, Lee, Jinho

Topic: Industrial Vision Systems and Defect Detection

Subfield: Industrial and Manufacturing Engineering

Field: Engineering

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7204915946

Cites:

Cited by:

Related to: