Training Deep Nets with Imbalanced and Unlabeled Data

Abstract

Training deep belief networks (DBNs) is normally done with large data sets. In this work, our goal is to predict {it traces} of the surface of the tongue in ultrasound images of the mouth during speech. Hand-tracing is labor-intensive; the dataset is highly imbalanced since many images are extremely similar. We propose a bootstrapping method which handles this imbalance by iteratively selecting a small subset of images to be hand-traced (thereby reducing human labor time), then (re)training the DBN, making use of an entropy-based diversity measure for the initial selection, thereby achieving a three-fold reduction in human time required for tracing with human-level accuracy.