Feature Purified Transformer With Cross-level Feature Guiding Decoder For Multi-class OOD and Anomaly Deteciton
This addresses the challenge of unsupervised anomaly and OOD detection in multi-class datasets for applications like industrial monitoring, though it appears incremental as it builds on existing reconstruction network methods.
The paper tackles the problem of reduced anomaly detection accuracy in multi-class datasets due to generalized reconstruction capabilities, introducing the FUTUREG framework with Feature Purification Module and CFG Decoder to enhance reconstruction error for anomalies. The result is state-of-the-art performance in multi-class OOD settings and competitive results in industrial anomaly detection.
Reconstruction networks are prevalently used in unsupervised anomaly and Out-of-Distribution (OOD) detection due to their independence from labeled anomaly data. However, in multi-class datasets, the effectiveness of anomaly detection is often compromised by the models' generalized reconstruction capabilities, which allow anomalies to blend within the expanded boundaries of normality resulting from the added categories, thereby reducing detection accuracy. We introduce the FUTUREG framework, which incorporates two innovative modules: the Feature Purification Module (FPM) and the CFG Decoder. The FPM constrains the normality boundary within the latent space to effectively filter out anomalous features, while the CFG Decoder uses layer-wise encoder representations to guide the reconstruction of filtered features, preserving fine-grained details. Together, these modules enhance the reconstruction error for anomalies, ensuring high-quality reconstructions for normal samples. Our results demonstrate that FUTUREG achieves state-of-the-art performance in multi-class OOD settings and remains competitive in industrial anomaly detection scenarios.