Active Decision Boundary Annotation with Deep Generative Models

Conference Paper (2017)
Author(s)

Miriam Huijser (Aiir Innovations)

Jan van Gemert (TU Delft - Pattern Recognition and Bioinformatics)

Research Group
Pattern Recognition and Bioinformatics
DOI related publication
https://doi.org/10.1109/ICCV.2017.565
More Info
expand_more
Publication Year
2017
Language
English
Research Group
Pattern Recognition and Bioinformatics
Pages (from-to)
5296-5305
ISBN (print)
978-1-5386-1033-6
ISBN (electronic)
978-1-5386-1032-9

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.

No files available

Metadata only record. There are no files for this record.