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

• URL: http://arxiv.org/abs/2508.11550v1
• Date: Fri, 15 Aug 2025 15:52:02 GMT
• Title: Training-Free Anomaly Generation via Dual-Attention Enhancement in Diffusion Model
• Authors: Zuo Zuo, Jiahao Dong, Yanyun Qu, Zongze Wu,
• Abstract summary: A growing body of works have emerged to address insufficient anomaly data via anomaly generation.<n>We propose a training-free anomaly generation framework dubbed AAG.<n>AAG is based on Stable Diffusion's strong generation ability for effective anomaly image generation.
• Score: 21.461351819711936
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Generate Aligned Anomaly: Region-Guided Few-Shot Anomaly Image-Mask Pair Synthesis for Industrial Inspection [53.137651284042434]
  Anomaly inspection plays a vital role in industrial manufacturing, but the scarcity of anomaly samples limits the effectiveness of existing methods.<n>We propose Generate grained Anomaly (GAA), a region-guided, few-shot anomaly image-mask pair generation framework.<n>GAA generates realistic, diverse, and semantically aligned anomalies using only a small number of samples.
  arXiv  Detail & Related papers  (2025-07-13T12:56:59Z)
• AnomalyHybrid: A Domain-agnostic Generative Framework for General Anomaly Detection [3.180143442781838]
  AnomalyHybrid is a domain-agnostic framework designed to generate authentic and diverse anomalies.<n>AnomalyHybrid is a Generative Adversarial Network(GAN)-based framework having two decoders that integrate the appearance of reference image into the depth and edge structures of target image respectively.
  arXiv  Detail & Related papers  (2025-04-06T03:28:30Z)
• GenIAS: Generator for Instantiating Anomalies in time Series [54.959865643340535]
  We develop a generative model for time series anomaly detection (TSAD) using a variational autoencoder.<n>GenIAS is designed to produce diverse and realistic synthetic anomalies for TSAD tasks.<n>Our experiments demonstrate that GenIAS consistently outperforms seventeen traditional and deep anomaly detection models.
  arXiv  Detail & Related papers  (2025-02-12T10:10:04Z)
• Dual-Interrelated Diffusion Model for Few-Shot Anomaly Image Generation [22.164957586513776]
  The performance of anomaly inspection in industrial manufacturing is constrained by the scarcity of anomaly data.<n>We propose DualAnoDiff, a novel diffusion-based few-shot anomaly image generation model.<n>Our approach significantly improves the performance of downstream anomaly inspection tasks, including anomaly detection, anomaly localization, and anomaly classification tasks.
  arXiv  Detail & Related papers  (2024-08-24T08:09:32Z)
• Unseen Visual Anomaly Generation [13.456240733175767]
  Anomaly Anything (AnomalyAny) is a novel framework that generates diverse and realistic unseen anomalies.<n>By conditioning on a single normal sample during test time, AnomalyAny is able to generate unseen anomalies for arbitrary object types with text descriptions.
  arXiv  Detail & Related papers  (2024-06-03T07:58:09Z)
• DiAD: A Diffusion-based Framework for Multi-class Anomaly Detection [55.48770333927732]
  We propose a Difusion-based Anomaly Detection (DiAD) framework for multi-class anomaly detection. It consists of a pixel-space autoencoder, a latent-space Semantic-Guided (SG) network with a connection to the stable diffusion's denoising network, and a feature-space pre-trained feature extractor. Experiments on MVTec-AD and VisA datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2023-12-11T18:38:28Z)
• AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model [59.08735812631131]
  Anomaly inspection plays an important role in industrial manufacture. Existing anomaly inspection methods are limited in their performance due to insufficient anomaly data. We propose AnomalyDiffusion, a novel diffusion-based few-shot anomaly generation model.
  arXiv  Detail & Related papers  (2023-12-10T05:13:40Z)
• Prototypical Residual Networks for Anomaly Detection and Localization [80.5730594002466]
  We propose a framework called Prototypical Residual Network (PRN) PRN learns feature residuals of varying scales and sizes between anomalous and normal patterns to accurately reconstruct the segmentation maps of anomalous regions. We present a variety of anomaly generation strategies that consider both seen and unseen appearance variance to enlarge and diversify anomalies.
  arXiv  Detail & Related papers  (2022-12-05T05:03:46Z)
• DVG-Face: Dual Variational Generation for Heterogeneous Face Recognition [85.94331736287765]
  We formulate HFR as a dual generation problem, and tackle it via a novel Dual Variational Generation (DVG-Face) framework. We integrate abundant identity information of large-scale visible data into the joint distribution. Massive new diverse paired heterogeneous images with the same identity can be generated from noises.
  arXiv  Detail & Related papers  (2020-09-20T09:48:24Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.