Anomaly detection (AD) is often framed as a representation-learning problem, where strong performance is expected to require learned features or AD-specific optimization. However, this view can overlo...
The paper explores how prior-data fitted networks (PFNs) can be adapted for anomaly detection in tabular data. Using frozen TabPFN features, the authors show that scoring samples by nearest-neighbor distance in feature space yields strong results, and they identify optimal layers and extraction procedures. They further improve performance by fine‑tuning the model on a reference set, achieving higher AUROC on the ADBench benchmark with both a fine‑tuning‑free (ZEN) and a fine‑tuned (FOCUS) approach.
arXiv:2608. 19463v1 Announce Type: new Abstract: Anomaly detection in tabular data is challenging because abnormal samples often arise as violations of cross-feature dependencies rather than simple marginal deviations.
arXiv:2610.28560v1 Announce Type: new Abstract: Visual anomaly detection aims to detect abnormal objects, while anomaly samples are often scarce during model training. Assembling multiple pretrained...
arXiv:2607. 23924v1 Announce Type: cross Abstract: Vision foundation models have enabled strong training-free anomaly detection (AD).
arXiv:2602.09593v2 Announce Type: replace-cross Abstract: Deep generative models with tractable likelihoods, exemplified by normalizing flows, offer an effective basis for anomaly detection through l...
Vision foundation models have enabled strong training-free anomaly detection (AD). However, most existing approaches rely primarily on independent local patch features, leaving the global contextual information encoded by Vision Transformers (ViTs) underexploited.
This paper introduces IDEAL, a framework for few-shot anomaly detection that uses both normal and anomalous reference examples. IDEAL suppresses irrelevant normal variations and encodes intrinsic deviation vectors that capture discriminative anomaly directions. Experiments on eight real-world datasets show that IDEAL generalizes to unseen anomalies and outperforms existing methods.
The paper introduces a training‑free anomaly detector that simultaneously handles structural and logical defects by calibrating heterogeneous anomaly cues with statistics from normal images. This calibration aligns frozen representations, allowing their fusion without extra training or part‑level supervision. The resulting method achieves state‑of‑the‑art AUROC scores on MVTec‑LOCO and remains competitive on MVTec‑AD.
The paper introduces PL‑SCEA, a method that reconfigures the attention mechanism of frozen Vision Foundation Models to better detect and localize anomalies in industrial images with few training examples. PL‑SCEA preserves the semantic context of pretrained query‑key attention while adding token‑adaptive self‑correlations over contextualized value features, then applies positive‑correlation filtering and power‑law reweighting to highlight task‑relevant relationships. The resulting features are fed into a lightweight variational autoencoder to produce reconstruction‑based anomaly scores, achieving competitive image‑level detection and strong pixel‑level localization on MVTec AD and VisA datasets.
arXiv:2609.36968v1 Announce Type: new Abstract: Unsupervised tabular anomaly detection (TAD) aims to identify anomalous rows in tabular data using normal training samples. While conventional methods...
The paper introduces a weakly supervised anomaly detection approach for tabular data that leverages universal semantic knowledge from a pre-trained foundation model and domain-specific features learned from the target dataset. A prototype‑conditioned modulation mechanism fuses these complementary representations, enabling them to reinforce each other for better anomaly detection. Experiments on public datasets demonstrate that the method outperforms existing competitors when only eight labeled anomalies are used during training.