Active Decision Boundary Annotation With Deep Generative Models

Miriam Huijser, Jan C. van Gemert; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 5286-5295

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 vector. A point on the decision boundary is revealed where the instances change class. Experimentally we show on three datasets that our method can be plugged-in to other active learning schemes, that human oracles can effectively annotate point on the decision boundary, and that decision boundary annotations improve over single sample instance annotations.

Related Material


[pdf] [Supp] [arXiv] [video]
[bibtex]
@InProceedings{Huijser_2017_ICCV,
author = {Huijser, Miriam and van Gemert, Jan C.},
title = {Active Decision Boundary Annotation With Deep Generative Models},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}
}