Information Condensing Active Learning
This addresses the challenge of efficient label acquisition in deep learning for researchers and practitioners, though it is incremental as it builds on existing batch mode active learning approaches.
The paper tackles the problem of selecting informative batches for labeling in deep Bayesian active learning by introducing ICAL, a method that uses HSIC to measure dependency between candidate batches and the unlabeled set, resulting in significant improvements in model accuracy and negative log likelihood on image datasets compared to state-of-the-art methods.
We introduce Information Condensing Active Learning (ICAL), a batch mode model agnostic Active Learning (AL) method targeted at Deep Bayesian Active Learning that focuses on acquiring labels for points which have as much information as possible about the still unacquired points. ICAL uses the Hilbert Schmidt Independence Criterion (HSIC) to measure the strength of the dependency between a candidate batch of points and the unlabeled set. We develop key optimizations that allow us to scale our method to large unlabeled sets. We show significant improvements in terms of model accuracy and negative log likelihood (NLL) on several image datasets compared to state of the art batch mode AL methods for deep learning.