Multi-Task Learning Based on Separable Formulation of Depth Estimation and Its Uncertainty
Abstract
We present an optimization framework for uncertainty estimation in a regression problem. To obtain predictive uncertainty inherent in the observation, we formulate regression with uncertainty estimation as a multi-task learning problem and a new uncertainty loss function, inspired by variational representations of robust estimation. Contrary to existing approaches, our approach allows balancing between the predictive task loss and uncertainty estimation loss. We evaluate the efficacy of our approach on NYU Depth Dataset V2 and show that our proposed method consistently yields better performance than the previous approaches, for both depth and uncertainty estimation.
Cite
Text
Asai et al. "Multi-Task Learning Based on Separable Formulation of Depth Estimation and Its Uncertainty." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.Markdown
[Asai et al. "Multi-Task Learning Based on Separable Formulation of Depth Estimation and Its Uncertainty." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/asai2019cvprw-multitask/)BibTeX
@inproceedings{asai2019cvprw-multitask,
title = {{Multi-Task Learning Based on Separable Formulation of Depth Estimation and Its Uncertainty}},
author = {Asai, Akari and Ikami, Daiki and Aizawa, Kiyoharu},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2019},
pages = {21-24},
url = {https://mlanthology.org/cvprw/2019/asai2019cvprw-multitask/}
}