Why do angular margin losses work well for semi-supervised anomalous sound detection?

K Wilkinghoff, F Kurth - IEEE/ACM Transactions on Audio …, 2023 - ieeexplore.ieee.org
State-of-the-art anomalous sound detection systems often utilize angular margin losses to
learn suitable representations of acoustic data using an auxiliary task, which usually is a …

Empirical Analysis of Anomaly Detection on Hyperspectral Imaging Using Dimension Reduction Methods

D Kim, YH Park - arXiv preprint arXiv:2401.04437, 2024 - arxiv.org
Recent studies try to use hyperspectral imaging (HSI) to detect foreign matters in products
because it enables to visualize the invisible wavelengths including ultraviolet and infrared …

Kumap: Kernel Uniform Manifold Approximation and Projection for Out-of-sample Extensions Problem

R Ran, B Li, Y Zou - 2024 - researchsquare.com
Abstract Uniform Manifold Approximation and Projection (UMAP) is a popular dimensionality
reduction and visualization algorithm recently proposed and widely used in several fields …

Comparación de técnicas de análisis multivariado para detección de valores extremos con técnicas no supervisadas, una aplicación al caso de anomalías en …

JP Arroyo Castro - kerwa.ucr.ac.cr
Este trabajo consiste en comparar técnicas no supervisadas del análisis multivariado para
la detección de anomalías en el contexto de la contratación pública de bienes en Costa …

Anomaly Detection of Marine Seismic Airgun Signatures using Semi-Supervised Learning

G Ollivierre, I Rahaman… - 2021 IEEE International …, 2021 - ieeexplore.ieee.org
Marine Seismic sources (ie, Airguns) play an important role in geophysical prospecting at
sea. They produce seismic waves that propagate into the earth's surface, whereby sensitive …