Active Learning for Bayesian 3D Hand Pose Estimation
This work addresses 3D hand pose estimation for applications like human-computer interaction, but it is incremental as it builds on existing Bayesian and deep learning approaches.
The paper tackles 3D hand pose estimation by proposing a Bayesian approximation to a deep learning architecture, analyzing data and model uncertainties, and introducing a new acquisition function for active learning. The result is that their method outperforms baselines on three benchmarks and achieves the lowest errors with the least data.
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.