CAD 100K: A Comprehensive Multi-Task Dataset for Car Related Visual Anomaly Detection
This provides a standardized dataset for researchers in car manufacturing quality assessment, but it is incremental as it builds on existing anomaly detection methods by focusing on multi-task evaluation.
The authors tackled the lack of a unified benchmark for multi-task visual anomaly detection in car manufacturing by introducing the CAD Dataset, which contains over 100,000 images across 7 vehicle domains and 3 tasks, and they found that multi-task learning promotes task interaction and knowledge transfer while exposing conflicts.
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.