Benutzer: Gast  Login
Titel:

Auxiliary Tasks in Multi-task Learning

Dokumenttyp:
Zeitschriftenaufsatz
Autor(en):
Liebel, Lukas; Körner, Marco
Abstract:
Multi-task convolutional neural networks (CNNs) have shown impressive results for certain combinations of tasks, such as single-image depth estimation (SIDE) and semantic segmentation. This is achieved by pushing the network towards learning a robust representation that generalizes well to different atomic tasks. We extend this concept by adding auxiliary tasks, which are of minor relevance for the application, to the set of learned tasks. As a kind of additional regularization, they are expecte...     »
Stichworte:
Computer Vision; without_full_paper_review; multi-task; arxiv; lmf_mt
Zeitschriftentitel:
arXiv preprint arXiv:1805.06334
Jahr:
2018
Reviewed:
nein
Sprache:
en
WWW:
https://arxiv.org/abs/1805.06334
Status:
Preprint / submitted
 BibTeX