Pith. sign in

REVIEW 2 cited by

Hierarchical Gaussian Mixture Normalizing Flow Modeling for Unified Anomaly Detection

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

arxiv 2403.13349 v2 pith:CJVTRB6K submitted 2024-03-20 cs.LG cs.CV

classification cs.LGcs.CV
keywords gaussianunifiedanomalydetectionlatentmethodsmixturemodeling
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Unified anomaly detection (AD) is one of the most challenges for anomaly detection, where one unified model is trained with normal samples from multiple classes with the objective to detect anomalies in these classes. For such a challenging task, popular normalizing flow (NF) based AD methods may fall into a "homogeneous mapping" issue,where the NF-based AD models are biased to generate similar latent representations for both normal and abnormal features, and thereby lead to a high missing rate of anomalies. In this paper, we propose a novel Hierarchical Gaussian mixture normalizing flow modeling method for accomplishing unified Anomaly Detection, which we call HGAD. Our HGAD consists of two key components: inter-class Gaussian mixture modeling and intra-class mixed class centers learning. Compared to the previous NF-based AD methods, the hierarchical Gaussian mixture modeling approach can bring stronger representation capability to the latent space of normalizing flows, so that even complex multi-class distribution can be well represented and learned in the latent space. In this way, we can avoid mapping different class distributions into the same single Gaussian prior, thus effectively avoiding or mitigating the "homogeneous mapping" issue. We further indicate that the more distinguishable different class centers, the more conducive to avoiding the bias issue. Thus, we further propose a mutual information maximization loss for better structuring the latent feature space. We evaluate our method on four real-world AD benchmarks, where we can significantly improve the previous NF-based AD methods and also outperform the SOTA unified AD methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. INP-Former++: Advancing Universal Anomaly Detection via Intrinsic Normal Prototypes and Residual Learning

    cs.CV 2025-06 conditional novelty 6.0 of 10

    INP-Former++ detects image defects by extracting intrinsic normal prototypes from the test image itself and reconstructing only normal regions, achieving state-of-the-art results across single-class, multi-class, few-...

  2. Towards Zero-Shot Anomaly Detection and Reasoning with Multimodal Large Language Models

    cs.CV 2025-02 conditional novelty 6.0 of 10

    Anomaly-OV, trained on the new Anomaly-Instruct-125k dataset, improves zero-shot detection of image anomalies and their textual explanations over generalist MLLMs.

Pith tools