REVIEW 11 cited by
Explainable Deep Few-shot Anomaly Detection with Deviation Networks
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Existing anomaly detection paradigms overwhelmingly focus on training detection models using exclusively normal data or unlabeled data (mostly normal samples). One notorious issue with these approaches is that they are weak in discriminating anomalies from normal samples due to the lack of the knowledge about the anomalies. Here, we study the problem of few-shot anomaly detection, in which we aim at using a few labeled anomaly examples to train sample-efficient discriminative detection models. To address this problem, we introduce a novel weakly-supervised anomaly detection framework to train detection models without assuming the examples illustrating all possible classes of anomaly. Specifically, the proposed approach learns discriminative normality (regularity) by leveraging the labeled anomalies and a prior probability to enforce expressive representations of normality and unbounded deviated representations of abnormality. This is achieved by an end-to-end optimization of anomaly scores with a neural deviation learning, in which the anomaly scores of normal samples are imposed to approximate scalar scores drawn from the prior while that of anomaly examples is enforced to have statistically significant deviations from these sampled scores in the upper tail. Furthermore, our model is optimized to learn fine-grained normality and abnormality by top-K multiple-instance-learning-based feature subspace deviation learning, allowing more generalized representations. Comprehensive experiments on nine real-world image anomaly detection benchmarks show that our model is substantially more sample-efficient and robust, and performs significantly better than state-of-the-art competing methods in both closed-set and open-set settings. Our model can also offer explanation capability as a result of its prior-driven anomaly score learning. Code and datasets are available at: https://git.io/DevNet.
Forward citations
Cited by 11 Pith papers
-
Beyond Normal References: Discriminative Few-Shot Anomaly Detection
IDEAL learns intrinsic deviation vectors from normal and anomalous references via a Normal Variation Eraser and Intrinsic Deviation Encoder to score query deviations and generalize to unseen anomalies on eight datasets.
-
Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection
MPFM models flow matching velocity as a Gaussian mixture prior per normal class plus a mutual information regularizer to improve open-set anomaly detection over unimodal prototypes.
-
Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection
MPFM uses flow matching with a Gaussian mixture prior on the velocity field and a mutual information maximizer to improve open-set anomaly detection over unimodal prototype methods.
-
ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection
ArcAD is a plug-and-play push-pull calibration method that projects limited normal samples onto a hypersphere for compact clustering while synthesizing pseudo-anomalies and using real anomalies to refine the decision ...
-
ArcAD: Anomaly-Rectified Calibration for Cold-Start Supervised Anomaly Detection
Under cold-start scarcity, ArcAD's Sinkhorn-balanced hyperspherical clustering plus anomaly-guided repulsion lifts reconstruction-based anomaly detection, with the clearest gains (+3.7 to +11.2 I-AUROC) on large multi...
-
Beyond Normal References: Discriminative Few-Shot Anomaly Detection
IDEAL learns intrinsic deviation vectors via Normal Variation Eraser and Intrinsic Deviation Encoder to score query deviations for both seen and unseen anomalies in discriminative FSAD.
-
Anomaly-Preference Image Generation
Anomaly Preference Optimization reformulates anomaly image generation as preference learning using real anomalies for implicit alignment signals from denoising trajectories plus a time-aware capacity allocation module.
-
Anomaly-Preference Image Generation
Anomaly Preference Optimization reformulates anomalous image synthesis as preference learning with implicit alignment from real anomalies and a time-aware capacity allocation module for diffusion models to balance div...
-
Mixture Prototype Flow Matching for Open-Set Supervised Anomaly Detection
MPFM transforms normal features into a structured Gaussian mixture prototype space via a mixture velocity field and mutual information regularization to achieve state-of-the-art open-set supervised anomaly detection.
-
Distribution Prototype Diffusion Learning for Open-set Supervised Anomaly Detection
DPDL learns multiple Gaussian prototypes and a Schrödinger bridge diffusion process to enclose normal samples in a compact discriminative space while using hyperspherical dispersion to identify out-of-distribution ano...
-
Anomaly-Preference Image Generation
Anomaly Preference Optimization reformulates anomaly image generation as preference learning with implicit alignment from real anomalies and a time-aware capacity allocation module in diffusion models.
Discussion (0). Sign in to comment.