Single-Layer Distillation with Fourier Convolutions for Texture Anomaly Detection

In industrial quality control, detecting anomalies in visual textures is essential for ensuring product quality and operational efficiency. Early identification of defects prevents faulty items from reaching consumers, reduces waste, and maintains high standards of production. Numerous unsupervised anomaly detection methods heavily depend on the integration of multiple layers from various pretrained models, a selection often made through empirical means. We propose SingleNet, an innovative knowledge distillation approach tailored for fast unsupervised texture anomaly detection, using a single layer from a compact pretrained model. Contrary to the previous knowledge distillation approaches, our network leverages fast Fourier convolutions (FFC) to reconstruct a degraded version of the teacher extracted features. At test time, we employed a frequency-aware filtering mechanism to reduce reconstruction artifacts caused by discrepancies between teacher and student architectures. Empirical results demonstrate the efficacy of our approach, attaining state-of-the-art performance across evaluated datasets coupled with expedited high-speed inference.