Reducing Overlearning through Disentangled Representations by Suppressing Unknown Tasks

Existing deep learning approaches for learning visual features tend to overlearn and extract more information than what is required for the task at hand. From a privacy preservation perspective, the input visual information is not protected from the model; enabling the model to become more intellige...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Panwar, Naveen, Tater, Tarun, Sankaran, Anush, Mani, Senthil
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Computer Vision and Pattern Recognition Computer Science - Learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!