OFAL: An Oracle-Free Active Learning Framework

TL;DR

OFAL introduces an oracle-free active learning framework that leverages neural network uncertainty and generative models to select informative samples, reducing reliance on costly human labeling.

Contribution

This work presents a novel oracle-free active learning approach combining uncertainty quantification and generative models, enhancing data efficiency without human oracle dependence.

Findings

OFAL effectively identifies uncertain samples for improved learning.

The method reduces the need for human-labeled data.

OFAL outperforms traditional active learning methods in accuracy.

Abstract

In the active learning paradigm, using an oracle to label data has always been a complex and expensive task, and with the emersion of large unlabeled data pools, it would be highly beneficial If we could achieve better results without relying on an oracle. This research introduces OFAL, an oracle-free active learning scheme that utilizes neural network uncertainty. OFAL uses the model's own uncertainty to transform highly confident unlabeled samples into informative uncertain samples. First, we start with separating and quantifying different parts of uncertainty and introduce Monte Carlo Dropouts as an approximation of the Bayesian Neural Network model. Secondly, by adding a variational autoencoder, we go on to generate new uncertain samples by stepping toward the uncertain part of latent space starting from a confidence seed sample. By generating these new informative samples, we can perform active learning and enhance the model's accuracy. Lastly, we try to compare and integrate our method with other widely used active learning sampling methods.