Cargando…
Measuring internal inequality in capsule networks for supervised anomaly detection
In this paper we explore the use of income inequality metrics such as Gini or Palma coefficients as a tool to identify anomalies via capsule networks. We demonstrate how the interplay between primary and class capsules gives rise to differences in behavior regarding anomalous and normal input which...
Autores principales: | Kirillov, Bogdan, Panov, Maxim |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9363486/ https://www.ncbi.nlm.nih.gov/pubmed/35945420 http://dx.doi.org/10.1038/s41598-022-17734-7 |
Ejemplares similares
-
Semi-Supervised Anomaly Detection in Video-Surveillance Scenes in the Wild
por: Sarker, Mohammad Ibrahim, et al.
Publicado: (2021) -
Increasing the Generalization of Supervised Fabric Anomaly Detection Methods to Unseen Fabrics
por: Rippel, Oliver, et al.
Publicado: (2022) -
Anatomy-aware self-supervised learning for anomaly detection in chest radiographs
por: Sato, Junya, et al.
Publicado: (2023) -
Automated screening of computed tomography using weakly supervised anomaly detection
por: Hibi, Atsuhiro, et al.
Publicado: (2023) -
ECG-Based Semi-Supervised Anomaly Detection for Early Detection and Monitoring of Epileptic Seizures
por: Karasmanoglou, Apostolos, et al.
Publicado: (2023)