Conference paper Open Access

Towards Visual Anomaly Detection in Domains with Limited Amount of Labeled Data

Štepec, Dejan; Skočaj, Danijel


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>Anomaly detection in visual data refers to the problem of differentiating abnormal appearances from normal cases. Supervised approaches have been successfully applied to different domains, but require abundance of labeled data. Due to the nature of how anomalies occur and their underlying generating processes, it is hard to characterize and label them. Recent advances in deep generative based models have sparked interest towards applying such methods for unsupervised anomaly detection and have shown promising results in medical and industrial inspection domains.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "XLAB Research", 
      "@type": "Person", 
      "name": "\u0160tepec, Dejan"
    }, 
    {
      "affiliation": "University of Ljubljana", 
      "@type": "Person", 
      "name": "Sko\u010daj, Danijel"
    }
  ], 
  "headline": "Towards Visual Anomaly Detection in Domains with Limited Amount of Labeled Data", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2020-03-19", 
  "url": "https://zenodo.org/record/3935533", 
  "keywords": [
    "anomaly detection", 
    "unsupervised", 
    "deep-learning", 
    "autoencoders", 
    "generative adversarial networks"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.18690/978-961-286-337-1", 
  "@id": "https://doi.org/10.18690/978-961-286-337-1", 
  "@type": "ScholarlyArticle", 
  "name": "Towards Visual Anomaly Detection in Domains with Limited Amount of Labeled Data"
}
15
13
views
downloads
Views 15
Downloads 13
Data volume 175.2 MB
Unique views 13
Unique downloads 12

Share

Cite as