Local Novelty Detection in Multi-class Recognition Problems

By Paul Bodesheim, Alexander Freytag, Erik Rodner, Joachim Denzler. 2015

62 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Biomedical Engineering, Epidemiology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Terrance E. Boult
2. Manuel Günther
3. Ethan M. Rudd
4. Walter J. Scheirer
5. Akshay Raj Dhamija
6. Abhijit Bendale
7. Lalit P. Jain
8. James Henrydoss

In Epidemiology

1. Terrance E. Boult

Citations in the corpus

• Towards Open Set Deep Networks (2015, background): “Altough a range of algorithms has been developed to address this issue [4, 20, 21, 25, 2], performing open set recognition with deep networks has remained an unsolved problem.”
• Learning and the Unknown: Surveying Steps toward Open World Recognition (2019, background): “…Liu 2016; Rebuffi et al. 2017), • Natural Language (Prakhya, Venkataram, and Kalita 2017; Doan and Kalita 2017; Grave, Cisse, and Joulin 2017), • Novelty Detection (Bodesheim et al. 2015; Lazzaretti et al. 2016; Schultheiss et al. 2017), • Package Authentication (Schraml et al. 2017), • Unmanned…”
• The Extreme Value Machine (2015, background): “Other approaches exist for related problems involving unknown class data such as multi-class novelty detection [17], domain adaptation [18], and zero-shot classification [19].”