Skip to content

CDGP: Contrastive Dual Gaussian Processes for Weakly Supervised Anomaly Segmentation

Aug 2026 · arXiv.org · Vol abs/2608.18614 · 0 citations · 20 references
Computer Science

TL;DR

This work proposes Contrastive Dual Gaussian Processes (CDGP), a weakly supervised framework that models normal and anomaly inducing-variable predictive distributions over dense tokens, and ranks first among the evaluated methods on all MVTec AD~2 localization metrics and is first-place or competitive on KSDD2 and VisA.

Abstract

Industrial visual inspection must both decide whether a product is defective and localize the defect, yet pixel-level masks are costly to collect at scale. Most anomaly-segmentation methods learn only from defect-free images and score deviations from normality. A true defect and an unusual-but-normal region, however, can both deviate substantially and receive similarly high scores. We propose Contrastive Dual Gaussian Processes (CDGP), a weakly supervised framework that models normal and anomaly inducing-variable predictive distributions over dense tokens. Its posterior-dominance statistic standardizes their predictive-mean difference by the joint predictive uncertainty, providing both spatial evidence and image-level confidence. This evidence complements hierarchical normal-reconstruction residuals for fine localization. All calibration uses training data only, without human pixel annotations or test-time fitting. Across MVTec AD~2, KSDD2, and VisA, CDGP ranks first among the evaluated methods on all MVTec AD~2 localization metrics and is first-place or competitive on KSDD2 and VisA. Factorized and matched linear-head controls delimit the contribution and scope of the linear-kernel Gaussian process (GP) formulation.

View source

Similar papers

Open access Nov 2026

Reconstruction Discrepancy Modeling for Unified Multi-Class Industrial Anomaly Detection

Industrial anomaly detection commonly relies on normal images because representative samples of diverse defects are difficult to collect. In unified multi-class settings, a shared model must also accommodate product-specific normal appearances while identifying local defects. Feature reconstruction localizes anomalies...

Fu-Qin Deng, Nan-Ming Huang, W. Luo et al. · 0 citations
Sep 2026

SAFe: Segment-guided Aggregation of Feature Densities for Anomaly-aware Segmentation

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...

Anja Delić, Jurica Runtas, Marin Oršić et al. · 0 citations
Preprint Nov 2026

VerdictAD: Few-Shot Anomaly Detection via Decision-Guided Refinement

Detecting defects in real-world industrial inspection often requires learning from only a few normal images per category. Recent few-shot anomaly detection methods have achieved strong performance by measuring feature differences between query images and normal references. However, visual differences do not always indi...

Shang-Quan Sun, Wen-Jun Luo, Yuan-Zhi Wang et al. · 0 citations
Review Open access 2026

Visual-Only and Vision–Language Industrial Anomaly Detection Under Benchmarks and Limited-Data Settings

An experimental evaluation review of recent methods using common dataset splits, preprocessing procedures, and evaluation metrics, while retaining method-specific backbones, input resolutions, and optimization schedules shows that visual-only methods achieve the strongest peak performance on standard benchmarks, but be...

Atefeh Gilvari, Rajeev Verma, N. Kar et al. · 0 citations
Open access Oct 2026

Learning Constrained Embeddings for Anomaly Region Localization

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...

Ting-Yu Lu, Chih-Chang Yu, Hsu-Yung Cheng · 0 citations
Preprint Nov 2026

FATE: Fault-Aware Transfer Error for Unsupervised Anomaly Detection

We study unsupervised industrial anomaly detection in the single-class setting, where a detector learns only from normal images of one product category. Reconstruction-based detectors model normal features from a frozen encoder, but their target layers are usually chosen by architectural convention. We instead ask what...

Tao-An Wang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.