Hybrid Quantum-MambaVision: A Quantum-enhanced State Space Model for Calibrated Mixed-type Wafer Defect Detection

2026-05-13

AI Summary

This work addresses the challenging problem of multi-label wafer defect detection in semiconductor manufacturing, characterized by extreme class imbalance, high computational complexity, and overlapping defects that obscure root-cause signals. To tackle these issues, the authors propose a quantum-classical hybrid architecture that integrates a linear-complexity Mamba state space model for efficient long-range spatial dependency modeling, a parameterized Quantum Context Adapter (QCA) serving as an uncertainty calibrator, and a fusion of Low-Rank Adaptation (LoRA) with quantum regularization to project compressed features into a high-dimensional Hilbert space for disentangling overlapping defects. Evaluated on the MixedWM38 dataset, the proposed method significantly reduces multi-defect misclassification rates, substantially lowers the maximum calibration error (MCE), and effectively constrains the expected false alarm cost.

Abstract

Extracting actionable knowledge from industrial visual data is fundamentally bottlenecked by extreme class imbalance and the prohibitive computational complexity of modern foundation models. In semi-conductor manufacturing, identifying multi-label wafer defects is a complex spatial data mining task where overlapping patterns obscure critical root-cause signals. While Vision Transformers (ViTs) excel at global dependency extraction, their quadratic scaling renders them inefficient for high-throughput, real-time anomaly detection. To overcome these computational barriers, this paper introduces Hybrid Quantum-MambaVision, a highly efficient architecture tailored for spatial knowledge discovery. We integrate a linear-complexity State-Space Model (SSM) backbone with a Parameterized Quantum Context Adapter (QCA) and Low-Rank Adaptation (LoRA). The Mamba backbone efficiently captures long-range spatial dependencies, while the quantum adapter maps compressed latent features into a high-dimensional Hilbert space to disentangle complex, overlapping signatures. On the highly imbalanced MixedWM38 dataset, Hybrid Quantum-MambaVision achieves exceptional multi-label classification performance, significantly reducing the error rate on complex multi-defect topologies compared to classical baselines. The quantum regularizer acts as a profound uncertainty calibrator, substantially reducing Maximum Calibration Error (MCE) and minimizing expected false-positive costs. This work establishes a scalable Quantum-Classical hybrid paradigm for efficient representation learning in industrial data mining.

Problem

• wafer defect detection
• class imbalance
• computational complexity
• multi-label classification
• industrial visual data

Innovation

• Quantum-Classical Hybrid
• State Space Model
• Quantum Context Adapter
• Calibrated Defect Detection
• Low-Rank Adaptation