Abstract
We propose a Bayesian approximation to a deep learning architecture for 3D hand pose estimation. Through this framework, we explore and analyse the two types of uncertainties that are influenced either by data or by the learning capability. Furthermore, we draw comparisons against the standard estimator over three popular benchmarks. The first contribution lies in outperforming the baseline while in the second part we address the active learning application. We also show that with a newly proposed acquisition function, our Bayesian 3D hand pose estimator obtains lowest errors with the least amount of data. The underlying code is publicly available at: https://github.com/razvancaramalau/al_bhpe.
Original language | English |
---|---|
Title of host publication | 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) |
Subtitle of host publication | 03-08 January 2021 |
Publisher | IEEE Explore |
Pages | 3418-3427 |
Number of pages | 10 |
ISBN (Electronic) | 978-1-6654-0477-8 |
ISBN (Print) | 978-1-6654-4640-2 |
DOIs | |
Publication status | Published - 14 Jan 2021 |
Publication series
Name | IEEE Workshop on Applications of Computer Vision |
---|---|
Publisher | IEEE |
ISSN (Print) | 2472-6737 |
ISSN (Electronic) | 2642-9381 |
Bibliographical note
This work is partially supported by Huawei Technologies Co. and by EPSRC Programme Grant FACER2VM (EP/N007743/1). We also like to thank Anil Armagan for his insights and discussions.The underlying code is publicly available at: https://github.com/razvancaramalau/al_bhpe.