DINO-PCB: Two-stage vision foundation model pretraining and distillation for real-time circuit-board defect detection
Authors:
- Junjie KeJKJunjie Ke
- Lihuo HeLHLihuo He
- Jing ZhangJZJing Zhang
- Haiming WangHWHaiming Wang
- Yuqi JiYJYuqi Ji
- Hui ChenHCHui Chen
- Jie LiJLJie Li
- Sicheng ZhaoSZSicheng Zhao
- Guiguang DingGDGuiguang Ding
- Xinbo GaoXGXinbo Gao
- 26 June 2026
- journal article
- Published by Elsevier in Pattern Recognition
- Vol. 180
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Beijing Municipality
- National Natural Science Foundation of China
- National Major Science and Technology Projects of China
This publication has 32 references indexed in Scilit:
- YOLO-Pdd: A Novel Multi-scale PCB Defect Detection Method Using Deep Representations with Sequential Images2025
- GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Features2024
- A lightweight hierarchical aggregation task alignment network for industrial surface defect detectionExpert Systems with Applications, 2024
- YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information2024
- AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection2024
- Fast plug-in capacitors polarity detection with morphology and SVM fusion method in automatic optical inspection systemSignal, Image and Video Processing, 2023
- CS-ResNet: Cost-sensitive residual convolutional neural network for PCB cosmetic defect detectionExpert Systems with Applications, 2021
- End-to-End Object Detection with Transformers2020
- Microsoft COCO: Common Objects in Context2014
- Automated inspection of PCB components using a genetic algorithm template-matching approachThe International Journal of Advanced Manufacturing Technology, 2006