Multi-task visual anomaly detection is critical for car-related manufacturing quality assessment. However, existing methods remain task-specific, hindered by the absence of a unified benchmark for multi-task evaluation. To fill in this gap, We present the CAD Dataset, a large-scale and comprehensive benchmark designed for car-related multi-task visual anomaly detection. The dataset contains over 100 images crossing 7 vehicle domains and 3 tasks, providing models a comprehensive view for car-related anomaly detection. It is the first car-related anomaly dataset specialized for multi-task learning(MTL), while combining synthesis data augmentation for few-shot anomaly images. We implement a multi-task baseline and conduct extensive empirical studies. Results show MTL promotes task interaction and knowledge transfer, while also exposing challenging conflicts between tasks. The CAD dataset serves as a standardized platform to drive future advances in car-related multi-task visual anomaly detection.
@article{arxiv.2604.09023,
title = {CAD 100K: A Comprehensive Multi-Task Dataset for Car Related Visual Anomaly Detection},
author = {Jiahua Pang and Ying Li and Dongpu Cao and Jingcai Luo and Yanuo Zheng and Bao Yunfan and Yujie Lei and Rui Yuan and Yuxi Tian and Guojin Yuan and Hongchang Chen and Zhi Zheng and Yongchun Liu},
journal= {arXiv preprint arXiv:2604.09023},
year = {2026}
}