Active Decision Boundary Annotation with Deep Generative Models

Miriam Huijser, Jan van Gemert

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

14 Citations (Scopus)

Abstract

This paper is on active learning where the goal is to reduce the data annotation burden by interacting with a (human) oracle during training. Standard active learning methods ask the oracle to annotate data samples. Instead, we take a profoundly different approach: we ask for annotations of the decision boundary. We achieve this using a deep generative model to create novel instances along a 1d line. A point on the decision boundary is revealed where the instances change class. Experimentally we show on three data sets that our method can be plugged into other active learning schemes, that human oracles can effectively annotate points on the decision boundary, that our method is robust to annotation noise, and that decision boundary annotations improve over annotating data samples.
Original languageEnglish
Title of host publication2017 IEEE International Conference on Computer Vision (ICCV)
EditorsL. O'Conner
Place of PublicationPiscataway
PublisherIEEE
Pages5296-5305
Number of pages10
ISBN (Electronic)978-1-5386-1032-9
ISBN (Print)978-1-5386-1033-6
DOIs
Publication statusPublished - 2017
Event2017 IEEE International Conference on Computer Vision (ICCV) - Venice, Italy
Duration: 22 Oct 201729 Oct 2017

Conference

Conference2017 IEEE International Conference on Computer Vision (ICCV)
Abbreviated titleICCV 2017
CountryItaly
CityVenice
Period22/10/1729/10/17

Keywords

  • Decoding
  • Gallium nitride
  • Computational modeling
  • Standards
  • Visualization
  • Learning systems
  • Predictive models

Fingerprint Dive into the research topics of 'Active Decision Boundary Annotation with Deep Generative Models'. Together they form a unique fingerprint.

  • Cite this

    Huijser, M., & van Gemert, J. (2017). Active Decision Boundary Annotation with Deep Generative Models. In L. O'Conner (Ed.), 2017 IEEE International Conference on Computer Vision (ICCV) (pp. 5296-5305). IEEE. https://doi.org/10.1109/ICCV.2017.565