Self-Supervised Learning in Multi-Task Graphs through Iterative Consensus Shift

The human ability to synchronize the feedback from all their senses inspired recent works in multi-task and multi-modal learning. While these works rely on expensive supervision, our multi-task graph requires only pseudo-labels from expert models. Every graph node represents a task, and each edge le...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2021-11
Hauptverfasser:	Haller, Emanuela, Burceanu, Elena, Leordeanu, Marius
Format:	Artikel
Sprache:	eng
Schlagworte:	Babies Domains Graph theory Ground truth Iterative methods Labels Learning Nodes Self-supervised learning Supervised learning Supervision
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!