A Multi-Category Anomaly Editing Network With Correlation Exploration and Voxel-Level Attention for Unsupervised Surface Anomaly Detection
- 16 September 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 7152-7167
Abstract
Developing a unified model for surface anomaly detection remains challenging due to significant variations across product categories. Recent feature editing methods, as a branch of image reconstruction, mitigate the over-generalization of auto-encoders that leads to accurate anomaly reconstruction. However, these methods are only suited for texture-category products and have significant limitations in being generalized to other categories. In this article, we propose a multi-category anomaly editing network with a dual-branch training approach: one branch processes defect-free images (normal branch), while the other handles synthetic anomaly images (anomaly branch). Specifically, the paired samples are first fed into the multi-category anomaly feature editing based auto-encoder (MCAFE-AE) to perform image reconstruction and inpainting. In the normal branch, we propose a dual-entropy constrained deep embedded clustering module (DEC-DECM) to promote a more compact and orderly distribution of normal latent features, while avoiding trivial clustering solutions. Based on the clustering results, we further design a patch-based adaptive thresholding (PAT) strategy to adaptively calculate the threshold representing the central boundary of the cluster center for each local patch, thereby enabling the model to detect anomalies. Then, in the anomaly branch, we propose a multi-category anomaly feature editing module (MCAFEM) to identify anomalies in synthetic images and apply a category-oriented feature editing strategy to transform detected anomaly features into normal ones, thereby suppressing the reconstruction of anomalies. After completing the image reconstruction and inpainting, the input images from both branches and their respective output images are concatenated and fed into the correlation exploration and voxel-level attention based prediction network (CEVA-Net) for anomaly segmentation. The network is integrated with our proposed correlation-dependency exploration and voxel-level attention refinement module (CDE-VARM) and generates precise anomaly maps under the guidance of the bidirectional-path feature fusion (BPFF) and deep supervised learning (DSL). Extensive experiments on three datasets show that our method achieves state-of-the-art performance.Keywords
Funding Information
- “Pioneer” and “Leading Goose” Research and Development Program of Zhejiang (2025C01037)
- National Natural Science Foundation of China (U21A20514)
- Key Research and Development Program Project of Hangzhou (2024SZD1A03)
- Ningbo Major Research and Development Plan Project (2024Z114)
This publication has 45 references indexed in Scilit:
- PixOOD: Pixel-Level Out-of-Distribution Detection2024
- MemSeg: A semi-supervised method for image surface defect detection using differences and commonalitiesEngineering Applications of Artificial Intelligence, 2023
- SPot-the-Difference Self-supervised Pre-training for Anomaly Detection and Segmentation2022
- Video anomaly detection with spatio-temporal dissociationPattern Recognition, 2022
- Reconstruction by inpainting for visual anomaly detectionPattern Recognition, 2021
- PaDiM: A Patch Distribution Modeling Framework for Anomaly Detection and Localization2021
- Clustering Driven Deep Autoencoder for Video Anomaly Detection2020
- GANomaly: Semi-supervised Anomaly Detection via Adversarial Training2019
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- What are Textons?International Journal of Computer Vision, 2005