Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: So, Yulim, Kang, Seokho
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.06687
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918193345331200
author So, Yulim
Kang, Seokho
author_facet So, Yulim
Kang, Seokho
contents Anomaly generation has been widely explored to address the scarcity of anomaly images in real-world data. However, existing methods typically suffer from at least one of the following limitations, hindering their practical deployment: (1) lack of visual realism in generated anomalies; (2) dependence on large amounts of real images; and (3) use of memory-intensive, heavyweight model architectures. To overcome these limitations, we propose AnoStyler, a lightweight yet effective method that frames zero-shot anomaly generation as text-guided style transfer. Given a single normal image along with its category label and expected defect type, an anomaly mask indicating the localized anomaly regions and two-class text prompts representing the normal and anomaly states are generated using generalizable category-agnostic procedures. A lightweight U-Net model trained with CLIP-based loss functions is used to stylize the normal image into a visually realistic anomaly image, where anomalies are localized by the anomaly mask and semantically aligned with the text prompts. Extensive experiments on the MVTec-AD and VisA datasets show that AnoStyler outperforms existing anomaly generation methods in generating high-quality and diverse anomaly images. Furthermore, using these generated anomalies helps enhance anomaly detection performance.
format Preprint
id arxiv_https___arxiv_org_abs_2511_06687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer
So, Yulim
Kang, Seokho
Computer Vision and Pattern Recognition
Anomaly generation has been widely explored to address the scarcity of anomaly images in real-world data. However, existing methods typically suffer from at least one of the following limitations, hindering their practical deployment: (1) lack of visual realism in generated anomalies; (2) dependence on large amounts of real images; and (3) use of memory-intensive, heavyweight model architectures. To overcome these limitations, we propose AnoStyler, a lightweight yet effective method that frames zero-shot anomaly generation as text-guided style transfer. Given a single normal image along with its category label and expected defect type, an anomaly mask indicating the localized anomaly regions and two-class text prompts representing the normal and anomaly states are generated using generalizable category-agnostic procedures. A lightweight U-Net model trained with CLIP-based loss functions is used to stylize the normal image into a visually realistic anomaly image, where anomalies are localized by the anomaly mask and semantically aligned with the text prompts. Extensive experiments on the MVTec-AD and VisA datasets show that AnoStyler outperforms existing anomaly generation methods in generating high-quality and diverse anomaly images. Furthermore, using these generated anomalies helps enhance anomaly detection performance.
title AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.06687