TDAD: Self-supervised industrial anomaly detection with a two-stage diffusion model

Wei, Changyun, Han, Hui, Xia, Yu and Ji, Ze ORCID: https://orcid.org/0000-0002-8968-9902 2025. TDAD: Self-supervised industrial anomaly detection with a two-stage diffusion model. Computers in Industry 164 , 104192. 10.1016/j.compind.2024.104192 Item availability restricted.

PDF - Accepted Post-Print Version Restricted to Repository staff only until 26 September 2026 due to copyright restrictions. Download (3MB)

Abstract

Visual anomaly detection has emerged as a highly applicable solution in practical industrial manufacturing, owing to its notable effectiveness and efficiency. However, it also presents several challenges and uncertainties. To address the complexity of anomaly types and the high cost associated with data annotation, this paper introduces a self-supervised learning framework called TDAD, based on a two-stage diffusion model. TDAD consists of three key components: anomaly synthesis, image reconstruction, and defect segmentation. It is trained end-to-end, with the goal of improving pixel-level segmentation accuracy of anomalies and reducing false detection rates. By synthesizing anomalies from normal samples, designing a diffusion model-based reconstruction network, and incorporating a multiscale semantic feature fusion module for defect segmentation, TDAD achieves state-of-the-art performance in image-level detection and anomaly localization on challenging and widely used datasets such as MVTec and VisA benchmarks.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Additional Information:	License information from Publisher: LICENSE 1: URL: http://creativecommons.org/licenses/by-nc-nd/4.0/, Start Date: 2026-09-26 Journal has embargo of 24 months. Awaiting further details from author in order to apply exception. I.R. (09/10/24)
Publisher:	Elsevier
ISSN:	0166-3615
Date of First Compliant Deposit:	9 October 2024
Date of Acceptance:	12 September 2024
Last Modified:	07 Nov 2024 19:15
URI:	https://orca.cardiff.ac.uk/id/eprint/172468

Actions (repository staff only)

Edit Item