Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/134827
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Episode-Based Active Learning with Bayesian Neural Networks |
Author: | Dayoub, F. Sunderhauf, N. Corke, P.I. |
Citation: | Conference on Computer Vision and Pattern Recognition Workshops IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops, 2017, vol.2017-July, pp.498-500 |
Publisher: | IEEE |
Issue Date: | 2017 |
Series/Report no.: | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
ISBN: | 9781538607336 |
ISSN: | 2160-7508 2160-7516 |
Conference Name: | IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (21 Jul 2017 - 26 Jul 2017 : Honolulu, Hawaii, USA) |
Statement of Responsibility: | Feras Dayoub, Niko Sunderhauf, Peter Corke |
Abstract: | 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. |
Keywords: | Training; Bayes methods; Robots; Neural networks; Tuning; Entropy; Conferences |
Rights: | © 2017 IEEE |
DOI: | 10.1109/CVPRW.2017.75 |
Grant ID: | http://purl.org/au-research/grants/arc/CE140100016 |
Published version: | https://ieeexplore.ieee.org/xpl/conhome/8014302/proceeding |
Appears in Collections: | Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.