tGARD: Text-Guided Adversarial Reconstruction for Industrial Anomaly Detection
- 1 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 21 (12) , 9297-9308
Abstract
Industrial anomaly detection aims to identify and localize defective regions in images. Among various architectures, reconstruction-based methods have demonstrated exceptional performance. These methods reconstruct anomalous samples into normal ones and identify anomalies through a comparison between them. However, reconstruction process within these methods often focuses on PL similarity, overlooking the high-frequency consistency between the input and output, which constrains the model’s accuracy. This article proposes tGARD, a novel text-guided adversarial reconstruction method for anomaly detection. Specifically, we introduce feature aggregation module, using nonlocal block and dilated convolution to handle complex anomaly patterns. Subsequently, text-guided reconstruction module is meticulously designed to harness CLIP’s multimodal alignment capabilities, allowing for a semantically controllable reconstruction process. This control is achieved by incorporating dynamic text embeddings derived from the CLIP encoder within discriminator. Meanwhile, during reconstruction process, high-frequency details are preserved through a convolutional adversarial discriminator. Finally, category-aware loss weighting strategy is conceived to balance similarity and adversarial loss. Experiments demonstrate that our model achieves significant improvements in anomaly localization, surpassing all reconstruction-based models on MVTec-AD. It also establishes a new state-of-the-art on VisA dataset, outperforming all existing architectures.Keywords
Funding Information
- National Natural Science Foundation of China (62472092, 62172089, 62106045)
- Natural Science Foundation of Jiangsu Province (BK20241751)
- Jiangsu Provincial Key Laboratory of Computer Networking Technology
- Jiangsu Provincial Key Laboratory of Network and Information Security (BM2003201)
- Key Laboratory of Computer Network and Information Integration of Ministry of Education of China (93K-9)
- Nanjing Purple Mountain Laboratories
This publication has 39 references indexed in Scilit:
- A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization2024
- GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection2024
- SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation2022
- DSR – A Dual Subspace Re-Projection Network for Surface Anomaly Detection2022
- CFA: Coupled-Hypersphere-Based Feature Adaptation for Target-Oriented Anomaly LocalizationIEEE Access, 2022
- ManiGAN: Text-Guided Image Manipulation2020
- MVTec AD — A Comprehensive Real-World Dataset for Unsupervised Anomaly Detection2019
- A Style-Based Generator Architecture for Generative Adversarial Networks2019
- Describing Textures in the Wild2014
- Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction2011