Color for object recognition: Hue and chroma sensitivity in the deep features of convolutional neural networks

In this work, we examined the color tuning of units in the hidden layers of AlexNet, VGG-16 and VGG-19 convolutional neural networks and their relevance for the successful recognition of an object. We first selected the patches for which the units are maximally responsive among the 1.2 M images of t...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Vision research (Oxford) 2021-05, Vol.182, p.89-100
Hauptverfasser:	Flachot, Alban, Gegenfurtner, Karl R.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Chroma responsivity Color Deep learning Feature visualization Hue selectitivity Neural Networks, Computer Object recognition Visual Perception
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!