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.
Waldstein, Ursula Schmidt-Erfurth, and Georg Langs
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Obtaining models that capture imaging markers relevant for disease progression and treatment monitoring is challenging. Models are typically based on large amounts of data with annotated examples of known markers aiming at automating detection. High annotation effort and the limitation to a vocabulary of known markers limit the power of such approaches. Here, we perform unsupervised learning to identify anomalies in imaging data as candidates for markers. We propose AnoGAN, a deep convolutional generative adversarial network to learn a manifold of normal anatomical variability, accompanying a novel anomaly scoring scheme based on the mapping from image space to a latent space. Applied to new data, the model labels anomalies, and scores image patches indicating their fit into the learned distribution. Results on optical coherence tomography images of the retina demonstrate that the approach correctly identifies anomalous images, such as images containing retinal fluid or hyperreflective foci.
years
2026 3representative citing papers
K-DSM uses per-feature kurtosis to set noise scales in DSM, enabling effective single-scale anomaly detection on tabular benchmarks in both semi-supervised and unsupervised settings.
Unsupervised anomaly detection model learns normative healthy retinal anatomy in OCT B-scans with discrete latent representations, layer-aware supervision and triplet learning, achieving AUROC 0.799 on Kermany and 0.884 cross-dataset on Srinivasan while providing pixel-level localization.
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.
-
Kurtosis-Guided Denoising Score Matching for Tabular Anomaly Detection
K-DSM uses per-feature kurtosis to set noise scales in DSM, enabling effective single-scale anomaly detection on tabular benchmarks in both semi-supervised and unsupervised settings.
-
Anatomy-Aware Unsupervised Detection and Localization of Retinal Abnormalities in Optical Coherence Tomography
Unsupervised anomaly detection model learns normative healthy retinal anatomy in OCT B-scans with discrete latent representations, layer-aware supervision and triplet learning, achieving AUROC 0.799 on Kermany and 0.884 cross-dataset on Srinivasan while providing pixel-level localization.