FFAD: Fixed-Position Few-Shot Anomaly Detection for Wire Harness Utilizing Vision-Language Models

Powei Liao, Pei-Chun Chien, Hiroki Tsukida, Yoichi Kato, Jun Ohya

2025

Abstract

Anomaly detection in wire harness assembly for automobiles is a challenging task due to the deformable nature of cables and the diverse assembly environments. Traditional deep learning methods require large datasets, which are difficult to obtain in manufacturing settings. To address these challenges, we propose Fixed-Position Few-Shot Anomaly Detection (FFAD), a method that leverages pre-trained vision-language models, specifically CLIP, to perform anomaly detection with minimal data. By capturing images from fixed positions and using position-based learnable prompts and visual augmentation, FFAD can detect anomalies in complex wire harness situations without the need for extensive data collection. Our experiments demonstrated that FFAD achieves over 90% accuracy with fewer than 16 shots per class, outperforming existing few-shot learning methods.

Paper Citation

in Harvard Style

Liao P., Chien P., Tsukida H., Kato Y. and Ohya J. (2025). FFAD: Fixed-Position Few-Shot Anomaly Detection for Wire Harness Utilizing Vision-Language Models. In Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM; ISBN 978-989-758-730-6, SciTePress, pages 647-656. DOI: 10.5220/0013164400003905

in Bibtex Style

@conference{icpram25,
author={Powei Liao and Pei-Chun Chien and Hiroki Tsukida and Yoichi Kato and Jun Ohya},
title={FFAD: Fixed-Position Few-Shot Anomaly Detection for Wire Harness Utilizing Vision-Language Models},
booktitle={Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM},
year={2025},
pages={647-656},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013164400003905},
isbn={978-989-758-730-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM
TI - FFAD: Fixed-Position Few-Shot Anomaly Detection for Wire Harness Utilizing Vision-Language Models
SN - 978-989-758-730-6
AU - Liao P.
AU - Chien P.
AU - Tsukida H.
AU - Kato Y.
AU - Ohya J.
PY - 2025
SP - 647
EP - 656
DO - 10.5220/0013164400003905
PB - SciTePress