BCLIP-ADer: A Bayesian Prompt Contrastive Language-Image Pretraining Method for Catenary Component Anomaly Detection in Electrified Railways
IEEE Transactions on Transportation Electrification · 2026-10 · 12 (5) · 7522-7534
DOI: 10.1109/tte.2026.3689522 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Transportation Electrification, 2026-10. Verfasst von Haonan Yang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Project of Natural Science Foundation of Sichuan Province.
Abstract (Originalsprache)
As an essential subsystem of electrified railway operation and maintenance, intelligent detection of catenary support components still faces several critical challenges: 1) the number of abnormal (negative) samples for components is severely limited; 2) component anomalies are highly diverse and exhibit heterogeneous visual characteristics; and 3) existing models generally show unsatisfactory detection performance when confronted with previously unseen anomaly types. To address these issues, this article proposes a novel few-shot anomaly detection model for catenary components, termed BCLIP-ADer, built upon a Bayesian prompt contrastive vision–language pretraining framework. Specifically, a Bayesian prompt-flow module (PFM) is designed to regularize the text prompt space via the jointly learned image-specific feature distribution (ISFD) and image-agnostic feature distribution (IAFD), thereby mitigating the degradation in detection performance on unseen component anomalies. Monte Carlo sampling (MCS) over these learned distributions is further employed to generate diverse text prompts, leading to more comprehensive coverage of the prompt space. In addition, a cross-modal feature refinement module (CFRM) is designed to more effectively align dynamic text embeddings with fine-grained image features, thus enhancing anomaly detection at the component level. Finally, extensive experiments conducted on the UAV-based catenary dataset (CSCUD) demonstrate the effectiveness and superiority of the proposed approach. Specifically, the proposed method achieves I-AUROC/I-AP/I-F1_max scores of 94.2/93.2/93.1 under few-shot conditions.
Förderung
- National Natural Science Foundation of China
- Key Project of Natural Science Foundation of Sichuan Province
Zitieren
APA
Yang, H., Hu, K., Wang, H., Hong, W., Wang, X., Wang, H., Song, Y., & Liu, Z. (2026). BCLIP-ADer: A Bayesian Prompt Contrastive Language-Image Pretraining Method for Catenary Component Anomaly Detection in Electrified Railways. IEEE Transactions on Transportation Electrification, 12(5), 7522-7534. https://doi.org/10.1109/tte.2026.3689522
Vancouver
Yang H, Hu K, Wang H, Hong W, Wang X, Wang H, et al. BCLIP-ADer: A Bayesian Prompt Contrastive Language-Image Pretraining Method for Catenary Component Anomaly Detection in Electrified Railways. IEEE Transactions on Transportation Electrification. 2026;12(5):7522-7534. doi:10.1109/tte.2026.3689522
BibTeX
@article{Yang2026,
author = {Yang, Haonan and Hu, Keting and Wang, Hui and Hong, Weijia and Wang, Xufan and Wang, Hongrui and Song, Yang and Liu, Zhigang},
title = {BCLIP-ADer: A Bayesian Prompt Contrastive Language-Image Pretraining Method for Catenary Component Anomaly Detection in Electrified Railways},
journal = {IEEE Transactions on Transportation Electrification},
year = {2026},
volume = {12},
number = {5},
pages = {7522--7534},
doi = {10.1109/tte.2026.3689522}
}
EUVIMED