Leveraging Color Channel Independence for Improved Unsupervised Object Detection

Object-centric architectures can learn to extract distinct object representations from visual scenes, enabling downstream applications on the object level. Similarly to autoencoder-based image models, object-centric approaches have been trained on the unsupervised reconstruction loss of images encod...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	Jäckl, Bastian, Metz, Yannick, Schlegel, Udo, Keim, Daniel A, Fischer, Maximilian T
Format:	Artikel
Sprache:	eng
Schlagworte:	Computer Science - Artificial Intelligence 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!