MIKLÁŠOVÁ, Kristína, Ondřej LOMIČ, Lukáš CÍSAR, Lubomír POPELÍNSKÝ and Veronika KREJČÍŘOVÁ. Autoencoders vs. others for anomaly detection. Online. In Jaroslav Zendulka, Mária Bieliková, Radek Burget, Zbyněk Křivka. DATA A ZNALOSTI & WIKT 2018, sborník konference. Brno: Vysoké učení technické v Brně, 2018, p. 215-220. ISBN 978-80-214-5679-2.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name Autoencoders vs. others for anomaly detection
Name in Czech Autoencodery vs. jiné metody pro detekci anomálií
Authors MIKLÁŠOVÁ, Kristína (703 Slovakia), Ondřej LOMIČ (203 Czech Republic), Lukáš CÍSAR (703 Slovakia), Lubomír POPELÍNSKÝ (203 Czech Republic, guarantor, belonging to the institution) and Veronika KREJČÍŘOVÁ (203 Czech Republic).
Edition Brno, DATA A ZNALOSTI & WIKT 2018, sborník konference, p. 215-220, 6 pp. 2018.
Publisher Vysoké učení technické v Brně
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 10200 1.2 Computer and information sciences
Country of publisher Czech Republic
Confidentiality degree is not subject to a state or trade secret
Publication form electronic version available online
RIV identification code RIV/00216224:14330/18:00105831
Organization unit Faculty of Informatics
ISBN 978-80-214-5679-2
Keywords (in Czech) Autoencodery · Local Outlier Factor (LOF) · z-skore · anomalie · PascalVOC image dataset · extrakce rysů
Keywords in English Autoencoders · Local Outlier Factor (LOF) · z-score · anomalies · PascalVOC image dataset · feature extraction
Tags International impact, Reviewed
Changed by Changed by: doc. RNDr. Lubomír Popelínský, Ph.D., učo 1945. Changed: 22/1/2019 22:40.
Abstract
The paper deals with a task of finding anomalies in the set of pictures using autoencoders and comparison of results with other methods searching for outliers, namely LOF and z-score. Outliers found by these methods are compared to outliers found by project team members. Process consists of preprocessing of pictures using pretrained deep neural nets (one at a time), reducing dimension using PCA, normalization of features and applying methods on pictures, either on a whole set or subsets divided by classes (dividing the pictures to groups by objects of interest that can be found in them). Output of methods with different attribute settings was compared to outliers found by team members using confusion matrix and F1-score. The results were not very positive, no significant relationships were found between anomalies found by team members and by anomalies found by individual methods. Possible reasons for this are discussed.
Abstract (in Czech)
The paper deals with a task of finding anomalies in the set of pictures using autoencoders and comparison of results with other methods searching for outliers, namely LOF and z-score. Outliers found by these methods are compared to outliers found by project team members. Process consists of preprocessing of pictures using pretrained deep neural nets (one at a time), reducing dimension using PCA, normalization of features and applying methods on pictures, either on a whole set or subsets divided by classes (dividing the pictures to groups by objects of interest that can be found in them). Output of methods with different attribute settings was compared to outliers found by team members using confusion matrix and F1-score. The results were not very positive, no significant relationships were found between anomalies found by team members and by anomalies found by individual methods. Possible reasons for this are discussed.
Links
MUNI/A/0854/2017, interní kód MUName: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace VII.
Investor: Masaryk University, Category A
PrintDisplayed: 23/7/2024 02:36