A few-shot enhancement method for railway foreign object detection using sample generation and transfer learning
Authors:
- Hang YuHYHang Yu
- Zhiwei CaoZCZhiwei Cao
- Yong QinYQYong Qin
- Tiantao XuTXTiantao Xu
- Tao JingTJTao Jing
- Zhenlin WeiZWZhenlin Wei
- 19 December 2025
- journal article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 166
Abstract
No abstract availableFunding Information
- National Key Research and Development Program of China (2023YFB3211103)
- Ministry of Science and Technology of the People's Republic of China
- China Postdoctoral Science Foundation (GZC20251118)
This publication has 20 references indexed in Scilit:
- Frontiers and developments of data augmentation for image: From unlearnable to learnableInformation Fusion, 2024
- Unveiling the potential of progressive training diffusion model for defect image generation and recognition in industrial processesNeurocomputing, 2024
- An Efficient Foreign Object Recognition Model in Rail Transit Based on Real-Time Railway Region Extraction and Object DetectionJournal of Electrical Engineering & Technology, 2024
- Re-scoring using image-language similarity for few-shot object detectionComputer Vision and Image Understanding, 2024
- Advancing Wildlife Protection: Mask R-CNN for Rail Track Identification and Unwanted Object DetectionIEEE Access, 2023
- Research on Active Safety Methodologies for Intelligent Railway SystemsEngineering, 2022
- Urban rail transit obstacle detection based on Improved R-CNNMeasurement, 2022
- An effective railway intrusion detection method using dynamic intrusion region and lightweight neural networkMeasurement, 2022
- Improved Mask R-CNN for obstacle detection of rail transitMeasurement, 2022
- Obstacle detection of rail transit based on deep learningMeasurement, 2021