arXiv AI
Why Does Counterintuitive Likelihood Behavior Rarely Emerge in Tabular Anomaly Detection?
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 30
TaskBridge: Bridging Unsupervised Tabular Anomaly Detection and In-Context Learning via Virtual Tasks
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...
arXiv AI
Jun 30
RGLD: Randomized Global-Local Density Estimation for Tabular Anomaly Detection
arXiv:2606. 28970v1 Announce Type: cross Abstract: Unsupervised tabular anomaly detection requires methods that are accurate, robust across heterogeneous datasets, and computationally efficient.
Hugging Face Trending Papers
Oct 5
Adapting prior-data fitted networks for tabular anomaly detection
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 Computer Vision
Sep 3
DPA: Decoupling Product-Agnostic Anomaly Representations for Zero-shot Anomaly Generation
The paper introduces DPA, a diffusion-based framework that decouples product-agnostic anomaly representations to enable zero-shot anomaly generation. By reusing real anomalies from existing source products and filtering them for plausibility, DPA learns product-irrelevant anomaly embeddings that can be transferred across products. An adaptive mask-guided pipeline and a training-free labeling module further refine the realism and localization of generated anomalies, leading to improved performance on MVTec-AD, VisA, and a new anomaly-transfer benchmark.
arXiv Machine Learning
Oct 19
Universal Semantic Enhancement for Weakly Supervised Anomaly Detection
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.
arXiv Machine Learning
Aug 3
Latent Sculpting for Zero-Shot Generalization: A Manifold Learning Approach to Out-of-Distribution Anomaly Detection
arXiv:2512. 22179v3 Announce Type: replace Abstract: Detecting previously unseen attacks remains a major challenge for machine learning-based intrusion detection systems.