A Casting Surface Dataset and Benchmark for Subtle and Confusable Defect Detection in Complex Contexts

Industrial anomaly detection (IAD) algorithms are essential for implementing automated quality inspection. Dataset diversity serves as the foundation for developing comprehensive detection algorithms. Existing IAD datasets focus on the diversity of objects and defects, overlooking the diversity of domains within the real data. To bridge this gap, this study proposes the Casting Surface Defect Detection (CSDD) dataset, containing 12,647 high-resolution gray images and pixel-precise ground truth labels for all defect samples. Compared to existing datasets, CSDD has the following two characteristics: 1.) The target samples are unaligned and have complex and variable context information. 2.) The defects in the CSDD dataset samples are subtle and confusable by factors such as oil contamination, processing features, and machining marks, illustrating the challenge of detecting real casting defects in an industrial context. Based on this dataset, we observe that current state-of-the-art (SOTA) IAD methods face challenges when there is considerable variation in sample context information. Furthermore, these methods encounter difficulties when abnormal samples are scarce, particularly those samples with subtle and confusable defects. To address this issue, we propose a novel method called Realistic Synthetic Anomalies (RSA), which enhances the model's capacity to construct a normal sample distribution by generating a large number of realistic synthetic anomalies. Experimental results demonstrate that the model trained to classify synthetic anomalies from normal samples achieves the highest accuracy for casting surface defect detection and significantly improves detection accuracy for subtle and confusable defects. The CSDD dataset and code of RSA are available at https://github.com/18894269590/RSA.