Episode-Based Active Learning with Bayesian Neural Networks
This addresses efficient data labeling for applications like mobile robotics, but it is incremental as it adapts existing methods to episodic settings.
The paper tackles active learning with Bayesian neural networks in episodic data scenarios, showing that incremental updates and final training on accumulated data achieve best performance on CIFAR-10 while reducing labeling effort.
We investigate different strategies for active learning with Bayesian deep neural networks. We focus our analysis on scenarios where new, unlabeled data is obtained episodically, such as commonly encountered in mobile robotics applications. An evaluation of different strategies for acquisition, updating, and final training on the CIFAR-10 dataset shows that incremental network updates with final training on the accumulated acquisition set are essential for best performance, while limiting the amount of required human labeling labor.