ExDD: Explicit Dual Distribution Learning for Surface Defect Detection via Diffusion Synthesis

TL;DR

ExDD introduces a dual distribution modeling framework using diffusion synthesis and memory banks to improve surface defect detection in manufacturing, surpassing traditional one-class anomaly detection methods.

Contribution

The paper presents a novel explicit dual distribution learning framework that models normal and anomalous features separately, utilizing diffusion models for synthetic defect generation and a neighborhood-aware scoring mechanism.

Findings

Achieved 94.2% I-AUROC on KSDD2

Optimal synthetic augmentation at 100 samples

Outperforms existing defect detection methods

Abstract

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 real-world 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. https://github.com/aqeeelmirza/ExDD-Defect-Detection