GATE-AD: Graph Attention Network Encoding For Few-Shot Industrial Visual Anomaly Detection

2026-03-16

AI Summary

This work addresses the challenge of industrial visual anomaly detection under extreme data scarcity, where only a few normal samples are available. The authors propose GATE-AD, a novel framework that introduces representation-aligned graph attention networks into the few-shot setting for the first time. Treating image patch-level features as graph nodes, the method models local non-Euclidean relationships through stacked self-attention layers and incorporates a learnable latent-space alignment mechanism alongside a new Scaled Cosine Error loss to enable precise defect localization. Evaluated on MVTec AD, VisA, and MPDD benchmarks, GATE-AD achieves state-of-the-art performance, improving image-level AUROC by up to 1.8% under an 8-sample setting while accelerating per-image inference by at least 25.05%.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Few-Shot Industrial Visual Anomaly Detection (FS-IVAD) comprises a critical task in modern manufacturing settings, where automated product inspection systems need to identify rare defects using only a handful of normal/defect-free training samples. In this context, the current study introduces a novel reconstruction-based approach termed GATE-AD. In particular, the proposed framework relies on the employment of a masked, representation-aligned Graph Attention Network (GAT) encoding scheme to learn robust appearance patterns of normal samples. By leveraging dense, patch-level, visual feature tokens as graph nodes, the model employs stacked self-attentional layers to adaptively encode complex, irregular, non-Euclidean, local relations. The graph is enhanced with a representation alignment component grounded on a learnable, latent space, where high reconstruction residual areas (i.e., defects) are assessed using a Scaled Cosine Error (SCE) objective function. Extensive comparative evaluation on the MVTec AD, VisA, and MPDD industrial defect detection benchmarks demonstrates that GATE-AD achieves state-of-the-art performance across the $1$- to $8$-shot settings, combining the highest detection accuracy (increase up to $1.8\%$ in image AUROC in the 8-shot case in MPDD) with the lowest per-image inference latency (at least $25.05\%$ faster), compared to the best-performing literature methods. In order to facilitate reproducibility and further research, the source code of GATE-AD is available at https://github.com/gthpapadopoulos/GATE-AD.

Problem

• Few-Shot Industrial Visual Anomaly Detection
• Anomaly Detection
• Industrial Inspection
• Small Sample Learning
• Visual Defect Detection

Innovation

• Graph Attention Network
• Few-Shot Anomaly Detection
• Representation Alignment
• Scaled Cosine Error
• Patch-level Feature Graph