CAD 100K: A Comprehensive Multi-Task Dataset for Car Related Visual Anomaly Detection
2026-04-10 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created the CAD Dataset, a large collection of images to help computers learn how to spot different types of problems in car parts all at once. This dataset includes pictures from several types of vehicles and tasks, making it unique for teaching multiple tasks together. They tested their approach and found that learning multiple tasks can help computers share knowledge but also introduces some difficulties. The CAD Dataset aims to help researchers improve how machines detect car defects in a more organized and comprehensive way.
visual anomaly detectionmulti-task learningcar manufacturingbenchmark datasetfew-shot learningdata augmentationvehicle domainsknowledge transfer
Authors
Jiahua Pang, Ying Li, Dongpu Cao, Jingcai Luo, Yanuo Zheng, Bao Yunfan, Yujie Lei, Rui Yuan, Yuxi Tian, Guojin Yuan, Hongchang Chen, Zhi Zheng, Yongchun Liu
Abstract
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.