The paper investigates why reconstruction-based unsupervised learning can fail, identifying two failure modes: over‑reconstruction of anomalies and loss of nominal variation. Using the Pursuit of Subspaces hypothesis, it links these failures to geometric properties—join blindness from excess range and meet preference from insufficient capacity—and shows that a compact nominal union is optimal, typically requiring a nonlinear reconstruction map. The authors propose Dynamic Push and Pull, along with nested manifold carving, to learn compact representations without anomaly labels, and demonstrate improved anomaly detection on standard benchmarks, unseen image degradations, and ECG classification.
arXiv:2507. 21164v2 Announce Type: replace-cross Abstract: Unsupervised anomaly detection (UAD) aims to detect anomalies without labeled data, a necessity in many machine learning applications where anomalous samples are rare or not available.
arXiv:2606. 15280v1 Announce Type: new Abstract: Most existing anomaly detection methods rely on estimating a probability density or learning an enclosing decision boundary, implicitly assuming that normal data occupies a region of non-zero volume in the ambient space.
The paper introduces NC‑TFAD, a task‑free continual anomaly detection framework that leverages neural‑collapse geometry to handle non‑stationary data streams in industrial visual inspection. It freezes a pretrained backbone, aligns streaming features to a simplex Equiangular Tight Frame prototype space, and uses synthetic anomaly anchors, inter‑ and intra‑class regularization, and a Focal Neural Collapse Contrastive loss to stabilize representations and enhance normal‑anomaly separability. A normal‑patch‑prototype‑guided localization branch generates calibrated anomaly heatmaps without pixel‑level annotations, and experiments on MVTec AD and VisA demonstrate that NC‑TFAD outperforms existing task‑free continual learning and unified anomaly detection baselines in both image‑level detection and pixel‑level localization.
The paper introduces NC‑TFAD, a task‑free continual anomaly detection framework that leverages neural‑collapse geometry to learn from non‑stationary data streams without task boundaries. It freezes a pretrained backbone, aligns streaming features to a simplex Equiangular Tight Frame prototype space, and uses synthetic anomaly anchors, inter‑ and intra‑class regularization, and a Focal Neural Collapse Contrastive loss to stabilize representations and enhance normal‑anomaly separability. A normal‑patch‑prototype‑guided localization branch generates calibrated anomaly heatmaps, and extensive experiments on MVTec AD and VisA demonstrate that NC‑TFAD outperforms existing task‑free continual learning and unified anomaly detection baselines in both image‑level detection and pixel‑level localization.
DIFFINT is a reconstruction‑based anomaly detector that replaces the opaque latent bottleneck of a standard autoencoder with a set of soft, axis‑aligned interval memberships learned directly from raw numerical data. Each latent unit represents a human‑readable hyper‑rectangle, and an instance’s anomaly score is its reconstruction error weighted by how strongly it falls inside these intervals. The method provides a certified lower bound on reconstruction error for points outside all active intervals, a graded suppression mechanism for sparse anomalies, and a closed‑form, label‑free importance ranking for each (unit, feature) pair, achieving top performance on 48 ADBench benchmarks against 22 baselines. whyItMatters":"DIFFINT offers the first interpretable anomaly detector that maintains competitive performance while revealing which feature ranges drive each anomaly score, enabling practitioners to audit and understand model decisions without requiring anomaly labels."
DIFFINT is a reconstruction‑based anomaly detector that uses a differentiable autoencoder with a latent bottleneck composed of soft, axis‑aligned interval memberships. Each latent unit represents a human‑readable hyper‑rectangle in feature space, allowing the model to encode how strongly an instance falls inside each interval and to compute reconstruction error as the anomaly score. The method provides a certified lower bound on reconstruction error for points outside all active intervals, a suppression mechanism for sparse abnormalities, and a closed‑form, label‑free importance ranking for each (unit, feature) pair, achieving top performance on 48 ADBench benchmarks against 22 baselines.
arXiv:2607. 20530v1 Announce Type: cross Abstract: Semi-supervised anomaly detection plays a key role in diverse fields such as process monitoring, healthcare, and finance.
arXiv:2601. 18823v4 Announce Type: replace Abstract: Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data.
arXiv:2606. 28268v1 Announce Type: cross Abstract: Test-time adaptation (TTA) has emerged as a promising paradigm for mitigating distribution shifts in deep models.
arXiv:2604. 19191v2 Announce Type: replace-cross Abstract: Deploying AI-based anomaly detection across diverse clinical imaging settings remains challenging because most existing methods rely on modality-specific architectures, anatomical priors, or extensive retraining, limiting their use as general-purpose screening tools.
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:2607. 00720v1 Announce Type: cross Abstract: Despite the increasing sophistication of industrial AI systems, the ability to reliably detect subtle and noisy anomalies in complex time series data remains a critical yet unresolved challenge.