CAD 100K: A Comprehensive Multi-Task Dataset for Car Related Visual Anomaly Detection

TL;DR

The paper introduces CAD 100K, a large-scale, multi-task dataset for car-related visual anomaly detection, enabling comprehensive evaluation and advancement in the field.

Contribution

It provides the first specialized multi-task dataset for car anomaly detection, including synthesis augmentation and baseline models for empirical studies.

Findings

Multi-task learning enhances task interaction and knowledge transfer.

Challenges include conflicts between tasks in multi-task learning.

The dataset enables standardized evaluation for future research.

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.