ExDD: Explicit Dual Distribution Learning for Surface Defect Detection via Diffusion Synthesis
This work addresses data scarcity and uniform outlier assumptions in industrial defect detection, offering a domain-specific improvement.
The paper tackles the limitations of one-class anomaly detection in industrial defect detection by proposing ExDD, a framework that models dual feature distributions and uses diffusion synthesis to generate synthetic defects, achieving 94.2% I-AUROC and 97.7% P-AUROC on KSDD2.
Industrial defect detection systems face critical limitations when confined to one-class anomaly detection paradigms, which assume uniform outlier distributions and struggle with data scarcity in realworld manufacturing environments. We present ExDD (Explicit Dual Distribution), a novel framework that transcends these limitations by explicitly modeling dual feature distributions. Our approach leverages parallel memory banks that capture the distinct statistical properties of both normality and anomalous patterns, addressing the fundamental flaw of uniform outlier assumptions. To overcome data scarcity, we employ latent diffusion models with domain-specific textual conditioning, generating in-distribution synthetic defects that preserve industrial context. Our neighborhood-aware ratio scoring mechanism elegantly fuses complementary distance metrics, amplifying signals in regions exhibiting both deviation from normality and similarity to known defect patterns. Experimental validation on KSDD2 demonstrates superior performance (94.2% I-AUROC, 97.7% P-AUROC), with optimal augmentation at 100 synthetic samples.