CVNov 10, 2025

AnoStyler: Text-Driven Localized Anomaly Generation via Lightweight Style Transfer

arXiv:2511.06687v11 citations
Originality Incremental advance
AI Analysis

This addresses the scarcity of anomaly data for computer vision applications, offering a more practical and efficient solution compared to prior methods.

The authors tackled the problem of generating realistic anomaly images for training anomaly detection models by proposing AnoStyler, a lightweight method using text-guided style transfer, which outperformed existing methods on MVTec-AD and VisA datasets and improved anomaly detection performance.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes