Active Decision Boundary Annotation With Deep Generative Models

摘要

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.