A4 Vertaisarvioitu artikkeli konferenssijulkaisussa
Weakly-Supervised Anomaly Detection for Multimodal Data Distributions
Tekijät: Tan, Xu; Chen, Junqi; Rahardja, Sylwan; Yang, Jiawei; Rahardja, Susanto
Toimittaja: N/A
Konferenssin vakiintunut nimi: IEEE International Conference on Signal Processing, Communications and Computing
Julkaisuvuosi: 2024
Journal: IEEE International Conference on Signal Processing, Communication and Computing
Kokoomateoksen nimi: 2024 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)
ISBN: 979-8-3503-6656-3
eISBN: 979-8-3503-6655-6
ISSN: 2375-8341
eISSN: 2837-116X
DOI: https://doi.org/10.1109/ICSPCC62635.2024.10770302
Verkko-osoite: https://ieeexplore.ieee.org/document/10770302
Preprintin osoite: https://arxiv.org/pdf/2406.09147
Weakly-supervised anomaly detection can outper-form existing unsupervised methods with the assistance of a very small number of labeled anomalies, which attracts increasing attention from researchers. However, existing weakly-supervised anomaly detection methods are limited as these methods do not factor in the multimodel nature of the real-world data distribution. To mitigate this, we propose the Weakly-supervised Variational-mixture-model-based Anomaly Detector (WVAD). WVAD excels in multimodal datasets. It consists of two components: a deep variational mixture model, and an anomaly score estimator. The deep variational mixture model captures various features of the data from different clusters, then these features are delivered to the anomaly score estimator to assess the anomaly levels. Experimental results on three real-world datasets demonstrate WVAD's superiority.