Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Model

2025-08-15 · Zuo Zuo, Jiahao Dong, Yanyun Qu, Zongze Wu arxiv

Industrial anomaly detection (AD) plays a significant role in manufacturing where a long-standing challenge is data scarcity. A growing body of works have emerged to address insufficient anomaly data via anomaly generation. However, these anomaly generation methods suffer from lack of fidelity or need to be trained with extra data. To this end, we propose a training-free anomaly generation framework dubbed AAG, which is based on Stable Diffusion (SD)'s strong generation ability for effective anomaly image generation. Given a normal image, mask and a simple text prompt, AAG can generate realistic and natural anomalies in the specific regions and simultaneously keep contents in other regions unchanged. In particular, we propose Cross-Attention Enhancement (CAE) to re-engineer the cross-attention mechanism within Stable Diffusion based on the given mask. CAE increases the similarity between visual tokens in specific regions and text embeddings, which guides these generated visual tokens in accordance with the text description. Besides, generated anomalies need to be more natural and plausible with object in given image. We propose Self-Attention Enhancement (SAE) which improves similarity between each normal visual token and anomaly visual tokens. SAE ensures that generated anomalies are coherent with original pattern. Extensive experiments on MVTec AD and VisA datasets demonstrate effectiveness of AAG in anomaly generation and its utility. Furthermore, anomaly images generated by AAG can bolster performance of various downstream anomaly inspection tasks.

📄 PDF Abstract BibTeX arXiv:2508.11550

Code (0)

등록된 구현이 없습니다.

Tasks

Anomaly Detection Image Generation

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

2026-03-18 · Haoxiang Rao, Zhao Wang, Chenyang Si, Yan Lyu 외 arxiv

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 …

Anomaly Detection

Human-Free Automated Prompting for Vision-Language Anomaly Detection: Prompt Optimization with Meta-guiding Prompt Scheme

2024-06-26 · Pi-Wei Chen, Jerry Chun-Wei Lin, Jia Ji, Feng-Hao Yeh 외

Pre-trained vision-language models (VLMs) are highly adaptable to various downstream tasks through few-shot learning, making prompt-based anomaly detection a promising approach. Traditional methods depend on human-crafte…

Anomaly Detection Anomaly Segmentation Few-Shot Learning

DeltaDeno: Zero-Shot Anomaly Generation via Delta-Denoising Attribution

2025-11-21 · Chaoran Xu, Chengkan Lv, Qiyu Chen, Yunkang Cao 외 arxiv

Anomaly generation is often framed as few-shot fine-tuning with anomalous samples, which contradicts the scarcity that motivates generation and tends to overfit category priors. We tackle the setting where no real anomal…

DSR -- A dual subspace re-projection network for surface anomaly detection

2022-08-02 · Vitjan Zavrtanik, Matej Kristan, Danijel Skočaj

The state-of-the-art in discriminative unsupervised surface anomaly detection relies on external datasets for synthesizing anomaly-augmented training images. Such approaches are prone to failure on near-in-distribution a…

Anomaly Detection Anomaly Localization Defect Detection Supervised Defect Detection+2

Component-aware Unsupervised Logical Anomaly Generation for Industrial Anomaly Detection

2025-02-17 · Xuan Tong, Yang Chang, Qing Zhao, Jiawen Yu 외

Anomaly detection is critical in industrial manufacturing for ensuring product quality and improving efficiency in automated processes. The scarcity of anomalous samples limits traditional detection methods, making anoma…