← Back to all news
Hugging Face Trending Papers

CDGP: Contrastive Dual Gaussian Processes for Weakly Supervised Anomaly Segmentation

Read the original on Hugging Face Trending Papers →

The paper introduces Contrastive Dual Gaussian Processes (CDGP), a weakly supervised approach for anomaly segmentation in industrial visual inspection. CDGP models normal and anomaly predictive distributions over dense tokens, using a posterior-dominance statistic that normalizes predictive-mean differences by joint uncertainty to provide spatial evidence and image-level confidence. The method achieves top performance on MVTec AD~2, KSDD2, and VisA datasets without requiring pixel-level annotations or test-time fitting.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at Hugging Face Trending Papers.

Related stories

Hugging Face Trending Papers
Jul 14

Statistical Non-linear Reconstruction Loss for Image Anomaly Detection

Reconstruction-based methods are a cornerstone of unsupervised image anomaly detection, but they remain vulnerable to \emph{outlier leakage}, where standard mean squared error (MSE) loss drives the model to faithfully reconstruct anomalous patterns. We propose a Non-linear Reconstruction Loss that applies a sigmoid-based squashing function to suppress high-magnitude features, preventing outliers from dominating optimization while preserving sensitivity to normal patterns.

benchmarks
More like this →
arXiv Computer Vision
Sep 4

ISP-AD: A Large-Scale Real-World Dataset for Advancing Industrial Anomaly Detection with Synthetic and Real Defects

The paper introduces ISP-AD, the largest publicly available industrial anomaly detection dataset, featuring both synthetic and real defects from a factory floor. It focuses on challenging, small, weakly contrasted surface defects within highly variable structured patterns, addressing the bias of existing datasets toward ideal imaging conditions. Experiments demonstrate that even a small amount of weakly labeled real defects improves model generalization and that synthetic defects can serve as a useful cold‑start baseline for scalable training.

By Paul J. Krassnig, Dieter P. Gruber
benchmarks
More like this →