A training-free method fits PCA to DINOv2 features from few normal images and detects anomalies via reconstruction residual, reaching SOTA one-shot AUROC of 97.1% image-level on MVTec-AD and 93.2% on VisA.
Improv- ing unsupervised defect segmentation by applying structural similarity to autoencoders
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
Convolutional autoencoders have emerged as popular methods for unsupervised defect segmentation on image data. Most commonly, this task is performed by thresholding a pixel-wise reconstruction error based on an $\ell^p$ distance. This procedure, however, leads to large residuals whenever the reconstruction encompasses slight localization inaccuracies around edges. It also fails to reveal defective regions that have been visually altered when intensity values stay roughly consistent. We show that these problems prevent these approaches from being applied to complex real-world scenarios and that it cannot be easily avoided by employing more elaborate architectures such as variational or feature matching autoencoders. We propose to use a perceptual loss function based on structural similarity which examines inter-dependencies between local image regions, taking into account luminance, contrast and structural information, instead of simply comparing single pixel values. It achieves significant performance gains on a challenging real-world dataset of nanofibrous materials and a novel dataset of two woven fabrics over the state of the art approaches for unsupervised defect segmentation that use pixel-wise reconstruction error metrics.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 5roles
background 1polarities
background 1representative citing papers
AnomalyVFM converts vision foundation models into zero-shot anomaly detectors via three-stage synthetic dataset generation plus low-rank adapters and weighted pixel loss, reaching 94.1% average image AUROC across nine datasets.
Real-IAD-MVN supplies multi-view normal vector data and a reconstruction baseline that outperforms prior multimodal methods for geometric industrial anomaly detection.
A new framework learns low-dimensional subspaces from nominal samples and reconstructs target deep embeddings via self-expressive linear combinations to localize anomalies, claiming SOTA on three benchmarks.
A text-semantics-guided multimodal framework with geometry-aware mapping and object-conditioned text adaptation achieves state-of-the-art unsupervised anomaly detection and localization on RGB-3D industrial datasets while enabling a single model for multiple classes.
citing papers explorer
-
SubspaceAD: Training-Free Few-Shot Anomaly Detection via Subspace Modeling
A training-free method fits PCA to DINOv2 features from few normal images and detects anomalies via reconstruction residual, reaching SOTA one-shot AUROC of 97.1% image-level on MVTec-AD and 93.2% on VisA.
-
AnomalyVFM -- Transforming Vision Foundation Models into Zero-Shot Anomaly Detectors
AnomalyVFM converts vision foundation models into zero-shot anomaly detectors via three-stage synthetic dataset generation plus low-rank adapters and weighted pixel loss, reaching 94.1% average image AUROC across nine datasets.
-
Real-IAD MVN: A Multi-View Normal Vector Dataset and Benchmark for High-Fidelity Industrial Anomaly Detection
Real-IAD-MVN supplies multi-view normal vector data and a reconstruction baseline that outperforms prior multimodal methods for geometric industrial anomaly detection.
-
Subspace-Guided Feature Reconstruction for Unsupervised Anomaly Localization
A new framework learns low-dimensional subspaces from nominal samples and reconstructs target deep embeddings via self-expressive linear combinations to localize anomalies, claiming SOTA on three benchmarks.
-
Text-Guided Multimodal Unified Industrial Anomaly Detection
A text-semantics-guided multimodal framework with geometry-aware mapping and object-conditioned text adaptation achieves state-of-the-art unsupervised anomaly detection and localization on RGB-3D industrial datasets while enabling a single model for multiple classes.