TY - GEN
T1 - Detection of High-Speed Railway Track Bed Foreign Object Based on Contrastive Learning and Adversarial Training
AU - Fan, Yupeng
AU - Dai, Peng
AU - Song, Haoran
AU - Li, Hongjue
N1 - Publisher Copyright:
© 2025 IEEE.
PY - 2025
Y1 - 2025
N2 - High-speed railway safety is compromised by track bed foreign objects, highlighting the imperative for efficient inspection. The track bed foreign objects detection is impeded by the rarity and diversity of those objects, resulting in challenges posed by limited and uncharacterized sample sets. This paper proposes a novel detection method based on contrastive learning and adversarial training, preserving the detection speed of one-stage detection while substantially enhancing accuracy. Contrastive learning sharpens feature discrimination, and adversarial training generates robust samples to bolster model performance. Experiments demonstrate that this approach yields a 12.9% increase in mAP.5 and 9.2% increase in mAP.5:.95, all without additional model parameters.
AB - High-speed railway safety is compromised by track bed foreign objects, highlighting the imperative for efficient inspection. The track bed foreign objects detection is impeded by the rarity and diversity of those objects, resulting in challenges posed by limited and uncharacterized sample sets. This paper proposes a novel detection method based on contrastive learning and adversarial training, preserving the detection speed of one-stage detection while substantially enhancing accuracy. Contrastive learning sharpens feature discrimination, and adversarial training generates robust samples to bolster model performance. Experiments demonstrate that this approach yields a 12.9% increase in mAP.5 and 9.2% increase in mAP.5:.95, all without additional model parameters.
KW - adversarial training
KW - contrastive learning
KW - foreign object of ballast bed
KW - one-stage object detection
UR - https://www.scopus.com/pages/publications/105002583887
U2 - 10.1109/ICPECA63937.2025.10928813
DO - 10.1109/ICPECA63937.2025.10928813
M3 - 会议稿件
AN - SCOPUS:105002583887
T3 - 2025 IEEE 5th International Conference on Power, Electronics and Computer Applications, ICPECA 2025
SP - 73
EP - 77
BT - 2025 IEEE 5th International Conference on Power, Electronics and Computer Applications, ICPECA 2025
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE International Conference on Power, Electronics and Computer Applications, ICPECA 2025
Y2 - 17 January 2025 through 19 January 2025
ER -