P ProtoDiffAD is proposed, a prototype-guided diffusion framework that represents each class using a dictionary of normal prototypes learned via a pretrained variational autoencoder, and Multi-Prototype Guidance (MPG) is introduced, which dynamically aggregates relevant prototypes through attention during denoising, enhancing anomaly localisation.
Abstract
Unsupervised Anomaly detection is important in industrial inspection and automation, where defects are rare, stochastic, and costly to annotate, while nominal data are abundant. Diffusion models have shown strong potential for unsupervised anomaly detection, where only normal data are available for training. However, standard class-conditional diffusion models rely on a single embedding per class, which insufficiently captures the multi-modal nature of normal distributions in unified multi-class settings. This coarse conditioning can yield over-generalised reconstructions that obscure anomalies or fail to preserve fine-grained normal structures. We propose ProtoDiffAD, a prototype-guided diffusion framework that represents each class using a dictionary of normal prototypes learned via a pretrained variational autoencoder. We further introduce Multi-Prototype Guidance (MPG), which dynamically aggregates relevant prototypes through attention during denoising. This mechanism enforces reconstruction fidelity to the normal manifold, enhancing anomaly localisation. Experiments on standard benchmarks (MVTec-AD and VisA) demonstrate consistent improvements over existing unified methods. The source code will be publicly available.
A locality-aware transformer network that enhances locality using Adaptive Neighbor Masked Attention and incorporates a Non-Local Token Enhancement Module (NL-TEM) to improve local feature representations and introduces a Layer-wise Query Decoder (LQD), which integrates intermediate encoder representations into the rec...
Industrial Anomaly Detection (IAD) aims to determine whether a product image contains defects and to localize anomalous regions. Since real anomalies are scarce, diverse, and difficult to acquire, many IAD methods rely on synthetic anomalies for training. However, localization performance heavily depends on how well sy...
Anomaly detection in noisy images is essential for quality control in industries like steel, composites, and textiles. Traditional unsupervised anomaly segmentation models, including Robust Principal Component Analysis and Smooth Sparse Decomposition, rely on restrictive data assumptions including anomaly sparsity and...
Mehrdad Moradi, K. Paynabar· IISE Annual Conference &...· 0 citations
Recent years have witnessed growing interest in continual anomaly detection for industrial visual inspection. However, real-world manufacturing environments exhibit unpredictable shifts in data distributions, rendering task-dependent continual learning assumptions impractical. To address this limitation, we formulate i...
Xiao-Tong Kong, Chao-Yang Song, Zi-Ai Zhou et al.· 0 citations
Visual segmentation systems encounter objects outside their training distribution during real-world deployment, hindering reliable autonomous systems that depend on scene parsing in the perception stage. Many recent methods address this by using self-supervised foundation models to train density estimators that yield l...
Industrial anomaly detection is a critical task in automated visual inspection systems, aiming to identify subtle defects without relying on large-scale anomaly annotations. Recently, pretrained vision transformers such as DINO have demonstrated strong feature representation capabilities and have been widely adopted in...
Chao-Qun Wang, Wen-Jing Zhang, Bo Qi et al.· Multimedia Systems· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.