LithoSeg: A Coarse-to-Fine Framework for High-Precision Lithography Segmentation

2025-11-14

AI Summary

To address low segmentation accuracy, poor robustness, and high annotation cost in trench profile extraction from lithographic scanning electron microscopy (SEM) images, this paper proposes a coarse-to-fine two-stage framework. First, a human-in-the-loop guided Segment Anything Model (SAM) initialization mechanism generates coarse-grained masks. Second, the 2D segmentation task is reformulated as a 1D point regression problem along the trench normal direction, incorporating normal-direction sampling and a lightweight multilayer perceptron (MLP) for pixel-level refinement. The method drastically reduces supervision requirements while achieving superior performance over state-of-the-art approaches in both segmentation IoU and critical dimension (CD) measurement error. This improvement enhances process control fidelity and semiconductor manufacturing yield, demonstrating strong potential for industrial deployment.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Security and Privacy: Large-scale security measurements

Abstract

Accurate segmentation and measurement of lithography scanning electron microscope (SEM) images are crucial for ensuring precise process control, optimizing device performance, and advancing semiconductor manufacturing yield. Lithography segmentation requires pixel-level delineation of groove contours and consistent performance across diverse pattern geometries and process window. However, existing methods often lack the necessary precision and robustness, limiting their practical applicability. To overcome this challenge, we propose LithoSeg, a coarse-to-fine network tailored for lithography segmentation. In the coarse stage, we introduce a Human-in-the-Loop Bootstrapping scheme for the Segment Anything Model (SAM) to attain robustness with minimal supervision. In the subsequent fine stage, we recast 2D segmentation as 1D regression problem by sampling groove-normal profiles using the coarse mask and performing point-wise refinement with a lightweight MLP. LithoSeg outperforms previous approaches in both segmentation accuracy and metrology precision while requiring less supervision, offering promising prospects for real-world applications.

Problem

• Achieving pixel-level groove contour segmentation in lithography SEM images
• Ensuring robust performance across diverse pattern geometries and processes
• Overcoming precision limitations of existing lithography segmentation methods

Innovation

• Coarse-to-fine network for lithography segmentation
• Human-in-the-Loop Bootstrapping with SAM model
• Recast 2D segmentation as 1D regression problem