preprint
Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce model
Julian
Lienen
author 44040
Eyke
Hüllermeier
author 48129
In many real-world applications, the relative depth of objects in an image is
crucial for scene understanding, e.g., to calculate occlusions in augmented
reality scenes. Predicting depth in monocular images has recently been tackled
using machine learning methods, mainly by treating the problem as a regression
task. Yet, being interested in an order relation in the first place,
ranking methods suggest themselves as a natural alternative to regression, and
indeed, ranking approaches leveraging pairwise comparisons as training
information ("object A is closer to the camera than B") have shown promising
performance on this problem. In this paper, we elaborate on the use of
so-called \emph{listwise} ranking as a generalization of the pairwise approach.
Listwise ranking goes beyond pairwise comparisons between objects and considers
rankings of arbitrary length as training information. Our approach is based on
the Plackett-Luce model, a probability distribution on rankings, which we
combine with a state-of-the-art neural network architecture and a sampling
strategy to reduce training complexity. An empirical evaluation on benchmark
data in a "zero-shot" setting demonstrates the effectiveness of our proposal
compared to existing ranking and regression methods.
2020
eng
arXiv:2010.13118
J. Lienen, E. Hüllermeier, ArXiv:2010.13118 (2020).
@article{Lienen_Hüllermeier_2020, title={Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce model}, journal={arXiv:2010.13118}, author={Lienen, Julian and Hüllermeier, Eyke}, year={2020} }
J. Lienen and E. Hüllermeier, “Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce model,” <i>arXiv:2010.13118</i>. 2020.
Lienen J, Hüllermeier E. Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce model. <i>arXiv:201013118</i>. 2020.
Lienen, Julian, and Eyke Hüllermeier. “Monocular Depth Estimation via Listwise Ranking Using the Plackett-Luce Model.” <i>ArXiv:2010.13118</i>, 2020.
Lienen, J., & Hüllermeier, E. (2020). Monocular Depth Estimation via Listwise Ranking using the Plackett-Luce model. <i>ArXiv:2010.13118</i>.
Lienen, Julian, and Eyke Hüllermeier. “Monocular Depth Estimation via Listwise Ranking Using the Plackett-Luce Model.” <i>ArXiv:2010.13118</i>, 2020.
202112020-10-27T07:48:40Z2022-01-06T06:54:23Z