One-to-More: High-Fidelity Training-Free Anomaly Generation with Attention Control

2026-03-18

AI Summary

This work addresses the challenge of industrial anomaly detection under extreme scarcity of anomalous samples, where existing few-shot generation methods often require time-consuming training and fail to faithfully replicate real anomaly distributions. To overcome these limitations, the authors propose O2MAG, a training-free few-shot anomaly generation approach that leverages self-attention from a single anomalous image to drive multiple diffusion processes in parallel. By integrating self-attention grafting, anomaly mask guidance, textual prompt alignment, and dual-attention enhancement, O2MAG generates high-fidelity, semantically consistent anomalous images. Experimental results demonstrate that the generated samples closely approximate the true anomaly distribution and significantly outperform state-of-the-art methods in downstream detection tasks, thereby substantially improving detection performance.

Technology Category

• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Industrial anomaly detection (AD) is characterized by an abundance of normal images but a scarcity of anomalous ones. Although numerous few-shot anomaly synthesis methods have been proposed to augment anomalous data for downstream AD tasks, most existing approaches require time-consuming training and struggle to learn distributions that are faithful to real anomalies, thereby restricting the efficacy of AD models trained on such data. To address these limitations, we propose a training-free few-shot anomaly generation method, namely O2MAG, which leverages the self-attention in One reference anomalous image to synthesize More realistic anomalies, supporting effective downstream anomaly detection. Specifically, O2MAG manipulates three parallel diffusion processes via self-attention grafting and incorporates the anomaly mask to mitigate foreground-background query confusion, synthesizing text-guided anomalies that closely adhere to real anomalous distributions. To bridge the semantic gap between the encoded anomaly text prompts and the true anomaly semantics, Anomaly-Guided Optimization is further introduced to align the synthesis process with the target anomalous distribution, steering the generation toward realistic and text-consistent anomalies. Moreover, to mitigate faint anomaly synthesis inside anomaly masks, Dual-Attention Enhancement is adopted during generation to reinforce both self- and cross-attention on masked regions. Extensive experiments validate the effectiveness of O2MAG, demonstrating its superior performance over prior state-of-the-art methods on downstream AD tasks.

Problem

• anomaly detection
• anomaly generation
• few-shot learning
• training-free
• industrial inspection

Innovation

• training-free
• anomaly generation
• attention control
• diffusion models
• few-shot synthesis