# Feature Perturbation Pool-based Fusion Network for Unified Multi-Class Industrial Defect Detection Source: [Feature Perturbation Pool-based Fusion Network for Unified Multi-Class Industrial Defect Detection]() Collection index: [llms.txt]() Data updated: 2026-04-23T05:00:05.535Z Authors: Yuanchan Xu, Wenjun Zang, Ying Wu Published: 2026-04-21T09:20:55.000Z ## Abstract Multi-class defect detection constitutes a critical yet challenging task in industrial quality inspection, where existing approaches typically suffer from two fundamental limitations: (i) the necessity of training separate models for each defect category, resulting in substantial computational and memory overhead, and (ii) degraded robustness caused by inter-class feature perturbation when heterogeneous defect categories are jointly modeled. In this paper, we present FPFNet, a Feature Perturbation Pool-based Fusion Network that synergistically integrates a stochastic feature perturbation pool with a multi-layer feature fusion strategy to address these challenges within a unified detection framework. The feature perturbation pool enriches the training distribution by randomly injecting diverse noise patterns -- including Gaussian noise, F-Noise, and F-Drop -- into the extracted feature representations, thereby strengthening the model's robustness against domain shifts and unseen defect morphologies. Concurrently, the multi-layer feature fusion module aggregates hierarchical feature representations from both the encoder and decoder through residual connections and normalization, enabling the network to capture complex cross-scale relationships while preserving fine-grained spatial details essential for precise defect localization. Built upon the UniAD architecture~\\cite{you2022unified}, our method achieves state-of-the-art performance on two widely adopted benchmarks: 97.17\\% image-level AUROC and 96.93\\% pixel-level AUROC on MVTec-AD, and 91.08\\% image-level AUROC and 99.08\\% pixel-level AUROC on VisA, surpassing existing methods by notable margins while introducing no additional learnable parameters or computational complexity. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Defect Localization on VisA (Accuracy %)](): Defect localization; VisA; Accuracy: 99.7. - [Defect Detection on MVTec-AD](): Defect Detection; MVTec AD; AUROC: 97.1. - [Anomaly Detection on VisA](): Anomaly Detection; VisA; AUROC: not recorded. - [Anomaly Localization on MVTec-AD (test)](): Anomaly Localization; MVTec-AD (test); Pixel AUROC: not recorded. ## Original sources and implementation [Original paper]() [PDF]()