STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Xichen, Wang, Yanshu, Wang, Jinbao, Zhang, Qunyi, Lei, Xiaoning, Xie, Guoyang, Jiang, Guannan, Lu, Zhichao
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911142861864960
author Xu, Xichen
Wang, Yanshu
Wang, Jinbao
Zhang, Qunyi
Lei, Xiaoning
Xie, Guoyang
Jiang, Guannan
Lu, Zhichao
author_facet Xu, Xichen
Wang, Yanshu
Wang, Jinbao
Zhang, Qunyi
Lei, Xiaoning
Xie, Guoyang
Jiang, Guannan
Lu, Zhichao
contents Segmentation-oriented Industrial Anomaly Synthesis (SIAS) plays a pivotal role in enhancing the performance of downstream anomaly segmentation, as it provides an effective means of expanding abnormal data. However, existing SIAS methods face several critical limitations: (i) the synthesized anomalies often lack intricate texture details and fail to align precisely with the surrounding background, and (ii) they struggle to generate fine-grained, pixel-level anomalies. To address these challenges, we propose Segmentation-oriented Anomaly synthesis via Graded diffusion with Explicit mask alignment, termed STAGE. STAGE introduces a novel anomaly inference strategy that incorporates clean background information as a prior to guide the denoising distribution, enabling the model to more effectively distinguish and highlight abnormal foregrounds. Furthermore, it employs a graded diffusion framework with an anomaly-only branch to explicitly record local anomalies during both the forward and reverse processes, ensuring that subtle anomalies are not overlooked. Finally, STAGE incorporates the explicit mask alignment (EMA) strategy to progressively align the synthesized anomalies with the background, resulting in context-consistent and structurally coherent generations. Extensive experiments on the MVTec and BTAD datasets demonstrate that STAGE achieves state-of-the-art performance in SIAS, which in turn enhances downstream anomaly segmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2509_06693
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment
Xu, Xichen
Wang, Yanshu
Wang, Jinbao
Zhang, Qunyi
Lei, Xiaoning
Xie, Guoyang
Jiang, Guannan
Lu, Zhichao
Computer Vision and Pattern Recognition
Segmentation-oriented Industrial Anomaly Synthesis (SIAS) plays a pivotal role in enhancing the performance of downstream anomaly segmentation, as it provides an effective means of expanding abnormal data. However, existing SIAS methods face several critical limitations: (i) the synthesized anomalies often lack intricate texture details and fail to align precisely with the surrounding background, and (ii) they struggle to generate fine-grained, pixel-level anomalies. To address these challenges, we propose Segmentation-oriented Anomaly synthesis via Graded diffusion with Explicit mask alignment, termed STAGE. STAGE introduces a novel anomaly inference strategy that incorporates clean background information as a prior to guide the denoising distribution, enabling the model to more effectively distinguish and highlight abnormal foregrounds. Furthermore, it employs a graded diffusion framework with an anomaly-only branch to explicitly record local anomalies during both the forward and reverse processes, ensuring that subtle anomalies are not overlooked. Finally, STAGE incorporates the explicit mask alignment (EMA) strategy to progressively align the synthesized anomalies with the background, resulting in context-consistent and structurally coherent generations. Extensive experiments on the MVTec and BTAD datasets demonstrate that STAGE achieves state-of-the-art performance in SIAS, which in turn enhances downstream anomaly segmentation.
title STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.06693