MulPViT-SimAM: An Electronic Substrate Defect Detection Framework for Addressing Class Imbalance Problems
Open Access
Abstract
As the cornerstone of contemporary electronics, the quality of electronic substrates—including Printed Circuit Boards (PCBs) and Ceramic Package Substrates (CPSs)—is intrinsic to product reliability. However, automated inspection is currently impeded by two persistent obstacles: the drastic multi-scale variation in defects and the acute class imbalance within defect datasets. Conventional deep learning approaches often fail to reconcile these challenges simultaneously, leading to suboptimal recognition of rare defect categories. To bridge this gap, we propose Multi-scale Partial Vision Transformer—Simple, Parameter-free Attention Module (MulPViT-SimAM), a robust framework designed for class-imbalanced electronic substrate defect detection. Our method features a novel multi-scale backbone (MulPViT) that synergizes partial convolutions with hierarchical attention mechanisms, facilitating the efficient extraction of both fine-grained local textures and global contextual dependencies. Additionally, we embed the Simple, Parameter-free Attention Module (SimAM) into the feature fusion stage to adaptively highlight defect-specific features while dampening background noise. To further mitigate data imbalance, we utilize the Equalized Focal Loss (EFL) function, which employs a category-specific modulating factor to dynamically equilibrate the learning focus across different classes. Comprehensive benchmarking reveals state-of-the-art performance, achieving mAP@0.5 scores of 95.7% on the standard PKU-MARKET-PCB dataset and 54.2% on the highly challenging CPS2D-AD dataset. Significantly, our approach effectively mitigates class imbalance, narrowing the performance deviation of rare categories to just 4.3% on the PKU-Market-PCB dataset and 1.4% on the CPS2D-AD dataset, compared to 11.8% and 7.5% in baseline models. These findings position MulPViT-SimAM as a viable and efficient solution for industrial quality control.Keywords
This publication has 38 references indexed in Scilit:
- MS-DETR: a real-time multi-scale detection transformer for PCB defect detectionSignal, Image and Video Processing, 2025
- Insulator defect detection based on BaS-YOLOv5Multimedia Systems, 2024
- A feature pyramid network with adaptive fusion strategy and enhanced semantic informationMultimedia Systems, 2024
- Vision Transformers with Hierarchical AttentionMachine Intelligence Research, 2024
- A detection network for small defects of steel surface based on YOLOv7Digital Signal Processing, 2024
- LDD-Net: Lightweight printed circuit board defect detection network fusing multi-scale featuresEngineering Applications of Artificial Intelligence, 2023
- Review of vision-based defect detection research and its perspectives for printed circuit boardJournal of Manufacturing Systems, 2023
- Exploring Plain Vision Transformer Backbones for Object Detection2022
- Class-discriminative focal loss for extreme imbalanced multiclass object detection towards autonomous drivingThe Visual Computer, 2021
- SSD: Single Shot MultiBox Detector2016