Generative OpenMax for multi-class open set classification

Zongyuan Ge, Sergey Demyanov, Zetao Chen, Rahil Garnavi

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

27 Citations (Scopus)

Abstract

We present a conceptually new and flexible method for multi-class open set classification. Unlike previous methods where unknown classes are inferred with respect to the feature or decision distance to the known classes, our approach is able to provide explicit modelling and decision score for unknown classes. The proposed method, called Generative OpenMax (G-OpenMax), extends OpenMax by employing generative adversarial networks (GANs) for novel category image synthesis. We validate the proposed method on two datasets of handwritten digits and characters, resulting in superior results over previous deep learning based method OpenMax Moreover, G-OpenMax provides a way to visualize samples representing the unknown classes from open space. Our simple and effective approach could serve as a new direction to tackle the challenging multi-class open set classification problem.

Original languageEnglish
Title of host publicationBritish Machine Vision Conference Proceedings 2017
EditorsKrystian Mikolajczyk, Gabriel Brostow
Place of PublicationLondon UK
PublisherBritish Machine Vision Association and Society for Pattern Recognition
Number of pages12
ISBN (Electronic)9781901725605
ISBN (Print)190172560X
DOIs
Publication statusPublished - 2017
Externally publishedYes
EventBritish Machine Vision Conference 2017 - Royal Geographic Society of London, London, United Kingdom
Duration: 4 Sep 20177 Sep 2017
Conference number: 28th
https://bmvc2017.london/
https://dblp.org/db/conf/bmvc/bmvc2017.html

Publication series

NameBritish Machine Vision Conference 2017, BMVC 2017

Conference

ConferenceBritish Machine Vision Conference 2017
Abbreviated titleBMVC 2017
CountryUnited Kingdom
CityLondon
Period4/09/177/09/17
Internet address

Cite this