Episode-Based Active Learning with Bayesian Neural Networks
By Feras Dayoub, Niko Sünderhauf, Peter Corke. 2017
10 citations recorded by the source corpus.
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.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Lei Tai
- Niko Sünderhauf
- Sergey Levine
- Dieter Fox
- Pieter Abbeel
- Chelsea Finn
- Yoshua Bengio
- Wolfram Burgard
Citations in the corpus
- The limits and potentials of deep learning for robotics (2018, methodology): “Some current approaches [24], [29] leverage the uncertainty estimation techniques based on approximate Bayesian inference (see Section II-A.1) to choose the most informative samples.”